Hacker News new | past | comments | ask | show | jobs | submit login
Ask HN: Those making $0/month or less on side projects – Show and tell
934 points by code_Whisperer on Jan 27, 2023 | hide | past | favorite | 1047 comments
Not sure about anyone else, but I enjoy seeing the posts on side projects making money. Often while reading all of the comments I find new products or services I want, so I buy them and contribute further to that hustle's success. But for every hacker making $100 or more per month with their idea, there are hundreds more working hard, making nothing, struggling to get started. Does that describe you? Maybe the community just needs to hear about what you're offering, what you've been working on. If you've got something cool that has not yet gained traction, maybe it just needs to be seen by a gaggle of like-minded hackers and geeks. So share!


<

SteamDB: https://steamdb.info/

I've been running it for over 10 years now, it's a database of Steam games, their updates, price history, charts, and a lot more.

In the early days we took monetary donations but stopped a few years in. It costs less than 100$ a month to run. Cloudflare reports 552.2M requests in the past 30 days, and 6.09M unique visitors.


You run SteamDB? Thanks for making this! I've used it for all those 10 years whenever I'm getting back into gaming and want to see what the popular games are! The player count charts are a really awesome feature. Thanks for keeping it running all these years.


Yes same here. Still use it to find upcoming trending games.


You're passing on $50k-100k per month of ad revenue from just basic banner ads... at least based on how RPMs were a few years ago. I respect that, definitely not the decision I'd make.


Even assuming a _very_ low $0.01/session, he'd be making $60k/mo.

More realistically, if he decided to do this right, and sell direct ads using something like Kevel, with "promoted" game slots or something on the homepage and search, he could do $10-$20CPM direct since it's a large and well known site with high purchase intent.

Let's say a conservative 4 impressions per page and 3 pages per session.

(12 imps per session * 6m sessions)/1000 * $10CPM is $720k / mo

This is a _very_ achievable number, quickly, for a site that is this close to purchase intent.

I don't understand. Even putting a single adsense ad at a $1 CPM would net him close to $20k/mo. This might be one of the least monetized sites I've seen at this scale.

Respect.


[flagged]


Comments like this make me wish I could downvote, but I don’t have the points. Live and let live, friend.


You clearly value different things to them, and that's okay.

To you, a big car or house may be a sign of success. To them, it might not be. Not everyone values material things the same.

It's clearly a considered decision. It's not stupid by any means, if this is what they want.


I’m extremely business minded but I don’t judge others this harshly for their own financial decisions.

Nicely fucking stupid? Give me a break.


You know nothing about this guy or his values. It can be just as stupid to harm a great accomplishment in order to drive a fancy car, so maybe let people have their own values


I see your maths here but Cloudflare hits include any assets, images, and so on so one page views fans out potentially dozens of hits. Cloudflare also includes all bots and non-human hits.


Page views are ~140 million per month: https://twitter.com/thexpaw/status/1604768632331870209/photo...

Assuming $0.50 net CPM on one AdSense unit per page view, that would be $70k monthly/$840k yearly revenue. And since operating cost is $100, that's all profit. I'm no AdSense expert but I believe this would be super conservative, maybe an expert could chime in with higher realistic numbers. Even if you don't like advertising there are other ways you could earn money with a site like SteamDB.


Cloudflare stats are inflated. I have a site getting 30k visits a day according to Google Analytics but Cloudflare says it's close to 100k. So I think Cloudflare doesn't filter out bots in their analytics.


Why are you doubting the numbers? All gamers use this site. Anything less than a huge number would be unthinkable.


I'm not doubting the stats, just saying that Cloudflare is not an accurate gauge of website views and visits. Cloudflare shows 3x the pageviews on my site than Google Analytics.


A man with two watches...

Why do you think google analytics is more right than cloudflare? Adblock can block GA, but it can't block cloudflare


Google analytics numbers don't include users with adblock


isn't that what you want if you want to calculate adsense revenue?


For page views (not "Visits") on my site, Cloudflare is within 10% of Google. Your experience doesn't necessarily apply universally.


I know nothing of this, but does .info reduce the numbers, compared to something like .com, all other things aside?

edit: err, it's a genuine question, from someone that doesn't work in/with advertising, and had a .info domain within the first month they were offered, in 2001. Here's a rephrasing: Do ad networks, or customers of those networks, treat TLDs differently?


He's doing us a favor by not plastering ads all over his site.


Yeah I wish I wasn't anti-ad but it's so bad... Ads between every paragraph or ads that pretend to be a virus so some fake Microsoft/Amazon scammer can get you to call them.

It's funny I wonder about the influence of ads too like you by using ad block experience a better internet (no influence on behavior).

There's a hijacking thing too of intent, at which point I modify websites to hide these above the fold attention grabbers.

My kindle forces you to read an ad everytime you turn it on. I know you could root it, lost money on device, etc...


Agree with you. Ads make sites look bad and I say this as an owner of several websites that run ads lol.

SteamDB looks pretty amazing and sleek without ads. Putting ads would only degrade the user experience and force people to install adblockers or use adblocking browsers like Brave. Kudos to xPaw for keeping his site ad-free for all of us to enjoy.


And he'll have my eternal respect for it.


Simply by the fact he runs SteamDB without monetization, I can safely assume he's much richer than me. I would'nt try to teaching someone who's richer than me how to make money.


He could sell ads for the Epic and GOG game stores!


Id rather make a loss than take money from Epic. Most unethical company. Makes steam look like saints.


Wow, you don't make any money on SteamDB? It seems like the sort of thing that should be able to make a lot of money. Even very minimal ads would probably bring in hundreds of thousands if not millions of dollars per year, and if you hate the idea of ads it seems like you could probably sell a premium subscription for some of the info you have that would be useful for devs, like imdb pro or crunchbase pro or something.


I can, but I have no interest in doing that currently.


As some others have said, affiliate is the way to go. You are already driving sales... Should be fair to you to get compensated.


Agree. Valve should probably find a way to compensate him. I've spent money on Steam because of his site.


If you don't mind me asking, what's your day job?


check his profile by clicking on id full stack developer per his home page


It's clear that he is a (very good!) full-stack developer. I am curious about where he works, or if he is retired or something, living off investments while working on SteamDB full time.

I think very few people would knowingly turn down income of a million dollars per year. In fact I'd say it's a privilege to be in a position to be able to turn that down. I even see some people here who are asking him to make the income even though he doesn't want it so he can give it to a charity.


I wouldnt be surprised if you could easily work out some sort of deal with Steam, if a game page from your site leads to a buy on their end they give you a small percentage.


I hate ads too. The thing I tried that felt ethical and useful was an affiliate code for related (to the content) products that would split the discount 50/50 between me and readers. I stated this clearly in the ad.


You're an absolute beast. Nice.


Legendary.


Valve should just acquire you to be honest.


No they should not, because they'd kill it or remove features, and god knows what else.


Not all heroes wear capes


Thank you!


Would be dope to monetize the traffic and donate it or support indie game projects.


Would you share more with us about the reason why you're not monetizing it?


Extremely baller


Does steam have some sort of affiliate link program? If they don't they should.


Many of us appreciate both the service and lack of ads. Thank you for both.


Can I ask if you might consider leveraging your position to aid a charity ?


This isn't a cost-free proposition. "giving away" money is a lot of work; leveraging an asset into money to donate is even more.


Agreed. Knowing the opportunity cost must weigh heavily. Bytes and Food. The new boots and cats.


Seems like the service itself is his choice of charity.


I'll do it?


kudos, mate


I completely respect the owner of SteamDB for not doing this... I'm not a fan of ad networks as it stands.

Although, affiliate links to games might be an idea (assuming Steam has such a thing). At least for the purchase if someone is interested in buying.


> affiliate links to games might be an idea (assuming Steam has such a thing).

Steam does not have such a thing.


Does Amazon still do affiliate links? Because they sell steam codes for games.


[flagged]


>You're a fan of taking things and not giving anything back, I see.

Don't be obtuse, that's not what he said and you know it.

Ad networks are problematic not because of the ads but because of the tracking and page bloat.

As he said affiliate links or some kind of custom non-tracking ads would be fine, and I'm not sure no one would be opposed to that.


> Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.


Avid user for years, so cool to see you on the social web! Thanks for your work! I'm annoyed for you at all these people trying to tell you what to do with your project, after you've been doing it successfully for 10 years and they have not. Y'all really think this person hasn't thought about monetizing? Take it easy startup-stans!


I can definitely see the frustration. Highly money-motivated people working their arse off to try and make even $1k MRR, and all this guy needs to do is push a button and he's got 100k. Must blow their minds.


I haven't read every comment, but I see a lot of surprise, a lot of respect and no annoyed/pissed off "startup-stans". Where are you getting this from?


You are an absolute chad. I salute you. Not to undermine your motive and intent, but people will gladly click on links to support your site. Regardless, what a legend you are.


I want to say thank you for building this, but also there's no shame in putting a simple banner ad somewhere on the page. Most people who care have ad blockers, anyways.


I'm not an user myself but since many comments chastise you of not making money with ads, I would like to thank you for your work and for keeping it free from ads


Yes, thanks for reminding me and everyone else that you can just do something nice for others and pay for it.

Maybe it is worth paying $0.00000018109 to satisfy someones request? If they are running up the bill to $0.00001642036 per person (90.6751339113 req/user/month) there must be something there worth something for them?

I get that some people are to cheap to purchase fun for others but at these rates it is more like people are against fun in general. One can be cheap but one cant be that cheap?

I've had this discussion before... uhh... a few times.

Them: Why are you doing this????

me: Aren't you having fun?

Them: YEAH, but why????

me: You see little jimmy over there? You think he is enjoying himself too?

Them: uh yes? But why????

me: Well, I don't mind it.


Amazing. What is your setup like to make costs so low, a lot of caching?


Bruh! I love this site. You absolutely could put ads here, in a way that isn't annoying.

I guarantee you that there are game shops out there that would pay you like $10k minimum to "Feature" their game for a month or something.

You feature 5 games a month for 10k, you suddenly are at 50k/mo.

Or, you could go the route of using traditional ads like google ads etc, but those can be kind of spammy and the ad targeting kind of sucks.

I'd really recommend exploring that, and don't feel bad about using ads. You deserve to get rewarded for the excellent site you've put together, a lot of people clearly get value out of it.


Impressive. What's your tech stack? How are you able to keep the cost so low?


php, nginx, mariadb (mysql). The stack that continues to deliver robust, low-cost, and reliable solutions yet HN shits on it at every opportunity.


It really is impressive how versatile that stack is, both on the low end and high. Wikipedia is also basically that stack too (just with apache instead, and varnish/ATS playing an important role)


nginx is decent to be fair


Assuming it hasn't changed in the past 2 years:

> nginx, latest php, mariadb.

> and of less importance: memcached and influxdb.

https://twitter.com/thexpaw/status/1315941483867000833


That's still correct.


What host do you use?


Hetzner.


I'd love to learn how you managed to scale on a single server - other than the above, any tips or tricks? I'm also a PHP guy on Ngnix with MySQL but want to know what tips you might have for a dynamic (non-static) site to handle such scale on a single server


Equip your server with a decent CPU, enough RAM to allow MySQL to keep most of your database in it, and fast SSDs. Profile your code and optimize/cache anything that stands out as slow, aggressively cache data that is read often using memcached/redis/etc, use an http cache proxy like cloudflare in front to cache static assets (and maybe pages that aren't dynamic for every user)


me also , how can it be 1 server ? how do you protect DDos attacks?


They use cloudflare in front, they do the heavy lifting.


Ty


Thanks!


When's the Next.js migration?


The amount of value I get out of your service is nuts! No better place to figure out whether a multiplayer game is worth getting... Daily users is hard metric to game or lie about.


I actually wouldn't mind some ads on this. Not the generic Google banner ads, but some cutesy illustrated banner in the style of Darkest Dungeon and such. Open an ad slot for bidding and the most interesting banner wins.


Wait, why are you not monetizing it? that traffic looks bonkers


Thankfully, some people out there still do things because they enjoy it and not because they think there's money to be made.


Most people who do things "just because", don't monetize because either it isn't possible or it isn't worth the effort. For a site with as much traffic as GP's, it's probably worth it. Regardless, anyone turning down that much revenue out of principle deserves a lot of credit.


That sounds like a pretty ideologically-motivated form of selection bias.


Well, my 2c is that making money is an enjoyable activity as well.

As someone who loved all the RTS/Tycoon games back in 2000's, I look at making money through own ventures as just another game at the same time


Sometimes making money off of something turns out to be incompatible with enjoyment, and you find out too late.

Depends on the person, how slippery the slippery slope is, and the motivation for a particular project.

I could ask myself "how much money would I be willing to pay to bring benefit to a large number of people?" It's definitely nonzero. But that's not a great question, because we all hate losing stuff we have (and paying is losing). It's a lot easier psychologically to forgo getting the money in the first place.

(Note that I wouldn't be able to forgo that much money. Though I might be able to procrastinate throwing the monetization switch for a while. How long is relative to my level of privilege in my own finances.)


Agreed. Depends on the personal point of view for every individual, and that's the reason I commented as my "2c". Personally, if I were the guy running the steamdb website I would have brought in the monetization aspect as quickly as possible, once I knew there was a lot of traffic coming in.


those two things are not always mutually exclusive


Monetizing something usually affects what you create as well as your experience creating it. It can easily be a negative effect.


I think Valve will shut it down once it learns about the monetization. AFAIK that is what happened to https://steamspy.com/ when they introduced paid subscription tier.


Valve didn't shut it down though. It just gave people privacy controls with sane defaults, cutting off data to scrapers. Not sure how much SteamDB depends on data like that but it seems to be doing fine.


The only explanation for why he is not monetising it is that he is Gabe Newell.


The fact the you choose to keep this project ad free is fire.


Thank you! I love the site. And also thank you for not having ads.


instant search is easily my favorite way to experience steamdb

to those who haven't used the tool (listed at bottom of page), it can be great for discoverability with a ton of filters, and quick responses

https://steamdb.info/instantsearch/


Why do you not take donations?


He does: https://steamdb.info/donate/ link is just above footer of main page.


That's a bit misleading. SteamDB don't accept monetary donations. Games are they only thing they accept donations of.


Games gifted to the bot are used to gain access to some extra info.

I do get game gifts to my personal account from time to time.


I will try to remember to donate games to you


Well as xPaw already stated he does not seem to interested in money. I would guess:

Give a Steam Award to xPaw

A Steam Award gives the creator of this site Steam points!

Is the best we can do to support his work! I just wanted to point there is a /donate. Not sure why it need to be cold hard cash to count.


I agree it is good to share that there is a donate page, but I also think it's a good thing to point out that they do not accept monetary donations.


"Currently we do not accept monetary donations"


Adding the donation link on the top banner should drive some donations. Currently, I can see it at the bottom.


I think you need to read that quote again.


Thanks for making this available. Has been a huge help over the years. Would make a good platform for other side projects (e.g. SteamDB YouTube) if you were to look for new challenges one day.


Had never seen your site before (stopped gaming before Steam became popular), but in visiting it now, very surprised to see that CS is still __by far__ the most popular online game.

Great resource. Thanks!


Kudos on the site & no ads.

Like others have said you could have affiliate deals with the game publishers direct, so there will be no in your face adverts.

You could also have banner ads that are complimentary.

Perhaps you don't need money, but personally I'd capture what I could as over 10 years that would be substantial.

You would then have extra reserve savings for yourself in case your circumstances change, or you could hand it over to charities

Love what you're doing regardless


Oh, cool, I used to run something very similar called steamwatch.com, back before they allowed you to have watch lists. It would monitor prices, let you know about sales, and I would occasionally run game give away raffles for free with whatever ad revenue I collected. It only ever made maybe $100 over its entire run. This would've been over 10 years ago though so I doubt mine and yours ever coexisted.


Huge fan here. It's impressive that it costs less than $100/month to run such a great service. Thank you so much.


Used it some years ago and thought that it was a really good front-end to the Steam store since the search interface is a bit lacking. Am surprised to see that this has millions of visitors but has such low running cost. Must be really highly optimized SQL queries and code there!


I would suggest you to place a donation regressive counter with the price that takes to make the website run, let's say 100 USD, everytime someone make a donation the value updates until it reaches the donation goal of the month.


How would you suggest starting data-mining for a project like this?

Every time I think of a project like this, I convince myself that steam/amazon/twitter/Facebook/etc will rate limit any bot that tries to scrape data from their service.


Thak you (and Marlamin) for SteamDB and especially for providing Linux filters as well as the steamdb IRC bot that you ran. Sad that you moved your channel off of IRC when Freenode died.

Respect for keeping the site ad-free.


I have used your site so many times. Thank you for all the work you’ve put into it.


Yeah making money from such website can be dangerous. You would get lawsuit from Valve


Valve is probably one of the least likely of companies to sue someone for doing something cool with their stuff.


I don't think so. If the owner monetize it, it's very likely ...


Hey there! Thanks for creating this site. Long time user here. It is an awesome product! I was curious about the system design diagram of SteamDb. What type of DB do you use to record historical prices?


thanks a lot for making this happen, in this exceptionally altruistic way, learning that such as staple as steamdb is a passion/hobby project really makes one believe in the software engineering mission


Just wanted to say big big fan. Have extensively used it during sales to see the lowest record prices. I absolutely love everything about the site, the design, the layout. Thank you for making it.


i am a bit late to comment but thanks for creating and maintaining the service for all this time! it really came in clutch when deciding on buying new games.

i am curious to hear from you about your experiences with people trying to scrape data off the site. i noticed that we cannot go back beyond a couple years for price history without logging in for one. is that a decision made because of people scraping data?


Thank you! SteamDB has been super helpful for me. I like to be able to pull posters and banner art for games, and it's also super helpful for untangling bundles of Rocksmith DLC.


Thank you very much! Your killer feature for me is being able to sort my library by fewest hours played and highest review rating so I get the best value out of my library.


I'm not a heavy Steam user, but SteamDB is great. Thank you!


As someone who played Fallout 4 with mods, thank you very much!


Dude take some revenue so you can continue doing cool stuff.


Wow, crazy to see how many players Unturned has. I used to love that game years ago. AFAIK it was created by a teenager at the time.


You're a hero to all gamers. Take a bow sir.


Are you independently wealthy from another project or inheritance?

Would you monetize it to fund a nonprofit or charity?


Holy cow, thank you so much for this resource.


Thanks so much. This site has helped me find new games, and it has saved me lots of money with the price history feature.


This is amazing! Is there a way to limit the charts to certain platforms only, like Mac or Linux compatible games?


I love your site! I suggest it to everyone.


Upvoting, as a Dota2 enjoyer/sufferer


I always wondered how Valve thinks about this project. And congrats on the project itself, for sure!


I know some Valve employees use it.


That's cool, thanks for the info!


I want you to know that I love you.


Steam should buy you , you are driving revenue for them.

I respect you for what you have done.


Cool! I've been recently using it to find free weekend games.


Wow, thank you for your work! Regularly use steamdb, lovely site!


Thank you! Love the site.


That's awesome! I've been using SteamDB for years.


You are a lifesaver. Cheers to you!


Make money through referer links?


Grew up using this. Thank you!


Big fan use it all the time


SteamDB is awesome!


I wonder what's the cost of running this ?


It's written right there in the comment.


But isn't it low compared the site visitors. I believe you run some servers to scrape the data from steam and save it somewhere right ?


Everything is done on a single server. What makes you think it's low?


The number of users maybe, with millions of users making requests to get the data, a $100 single server won't be able to handle the load. that's why i asked, anyway great achievement


Respect


Thank you!


amazing product.


Radiant: https://getradiant.app/

Premise: Takes your Spotify and turns it into a personalised FM-style radio station, complete with a snarky, AI-powered radio presenter called Rad.

Rad'll quip, read you the news and weather on the hour, announce what you've just heard and what's coming next, gives you biographical info for bands you might not be too familiar with but most importantly; Rad helps you discover new music while playing all the songs you know and love, in a smart, contextual way.

Availability: iOS, Android.

Price: $0

Cost to me: like 40-50 bucks a month.

Why do it? I use it daily and so do many others. Great for house parties, offices, long car journeys or just your daily pilgrimage to the supermarket.


Unsolicited feedback: If this were also offered as a web-based application I'd probably use it (sitting at my desk all day I don't want to use my mobile device for music). Maybe sell rotating ads or sponsorships (on screen but not in the audio stream, please!) to make some $.

Very cool.


That's exactly what is coming next for it! A fully-fledged web app. It's actually built using web tech so it's an easy port. Just need to rebuild some of the native bits for web (ohh I might get to use wasm!) but once that's done it should be good to go. Planning on pushing out in the next 2 weeks.

And yeah while I don't need to run ads on it at the moment, if the right sponsor wanted to work with me I'd be exceptionally happy to do so.


Doesn't Spotify have terms around not making money on any apps that use their API? From https://developer.spotify.com/policy/#iv-streaming-and-comme...

> Except for the limited commercial uses for Non-Streaming SDAs (set out below) commercial uses are not permitted for SDAs.

Their guidelines are super strict about using any music or artwork in specific ways. For instance, I'm pretty certain you need to display a Spotify logo any time you play music from Spotify, which I don't see on the player. And the player has rounded corners on the artwork.

Some excerpts from https://developer.spotify.com/documentation/general/design-a...

> To comply with our licensing agreements, you must always attribute content from Spotify with the logo.

> Artwork must be kept in its original form. Don’t animate or distort it in any way. This includes applying overlays and blurring.

I'm not a lawyer so I'm sorry if I'm reading these incorrectly. I tried making an app using the Spotify API at one point and had it running but it got shot down a couple times for not displaying the Spotify icon. Good on you if your app is all set. I was always worried I was going to face the Spotify legal team with mine and gave up on it.

I only mention these because I do love the radio! Great mix of genres so far!


Radiant launched with a paid subscription model (like a dollar a month) Spotify shut it down, took away our API creds and left us in the lurch. Had to set it up again, with the subscription removed. That hurt because we had a good number of paying customers at that point.

But we moved to be compliant with their guidelines after that and I carried it on as a labour of love.

Now I'm actively looking at moving away from Spotify and on to my own data set and APIs that can match what Spotify has. I've built something like it before using the Cover Art Archive for the artwork, Acoustic/MusicBrainz for the metadata and custom logic built atop so I know it's possible.

Once I've done that I can start looking for sponsors.

There is always the possibility that if the userbase really scales up, Spotify would grant me a commercial license and allow me to commoditise the platform but I don't need that to happen really.


How long did it take for them to notice?


I made a Spotify powered app ( https://mergemusic.app ) and we didn't add any payment methods to comply with their terms.

Tried for months / years to get in touch with someone at Spotify who could discuss a commercial licence agreement, so the app could have a business model. Stonewalled.

Turns out Spotify instead of working with us, made their own version - Spotify Blend, launched 2 years after our app.

The thing that bugs me the most is Spotify is a member of https://appfairness.org which states

> App store gatekeepers have carefully crafted their mobile device ecosystems to eliminate competition and maximize their own control and profits, to the detriment of developers and consumers.

However Spotify's own App Store did exactly the behaviour they are complaining about.


I suspect it might be complicated by the fact that most of their content isn't owned by them but leased(?) from record labels, artists, podcasters, etc?

But I agree it seems like they use this API as a free launch pad for ideas, which seems morally or ethically questionable. Sorry to hear they might have ripped your idea.


We weren't taking content. Just creating playlists back on Spotify through their API.


Same, won't use a mobile app but would happily use a web app.

Any plans for Youtube Music support? I rarely use spotify anymore. Not your problem obviously, just wondering if you have plans to expand.


I've got plans to build my own "open music API" that'll make whatever service you use just an adaptor that Rad can tap into. At the moment Radiant is very embedded in Spotify's API ecosystem due to a few key features none of the other services has.

Longer term thing sadly as this is very much my side deal but it'll get there.

Probably make that new API and dataset OSS as I want other devs to build cool stuff without being at the mercy of the streaming services.


Honestly, I think the value is in the DJ personalities. I'm trying to get away from sarcasm in my daily life as it makes me unhappy overall. Most evenings, I just kinda wanna listen to someone more positive like a dead head talk about music -- no offense, I just wanna look at the positive side of life for the years I have left.

That said, I would like to see even just a recommendation engine plug into YT Music, spotify, even hell, an nzb downloader. "You liked this song and band, you know you should try this band."


Very much hoping for some alternative services functionality — would love this in my shop. Cheers for an incredible idea!


If you want something like this for a shop or store etc, ping me via rad@getradiant.app, we might be able to build something cool to fit that need (I've been toying with this idea for a while so it'd be nice to have a first user for it)


I'm curious about the stack-- is the app React Native with some actual native modules, then? Or is it based on something like Ionic?


It was a native iOS app originally but now it's pure web (straight Svelte SPA, no UI framework) with native plugins.

I did it because I don't have the time to maintain for 3 platforms in parallel without one falling behind and I'm not a fan of React native personally. I spent a good chunk of time testing with much older hardware as a target to make sure performance wouldn't be a noticeable distraction for users and I'm happy with how it turned out :)


If you have more info on how you set up your Svelte project, I’d be interested in hearing! I recently rewrote my personal website from react into something much simpler with Svelte and am trying to figure out the best way to serve it on phones.


Hell, ads would even make it feel more like real radio. Bonus points if the "host" "reads" them.


If you're on an M1 MacBook, you can run the iPad app on it, pretty responsive.


Me three!


> If this were also offered as a web-based application I'd probably use it

#metoo


If anyone is interested in learning more, suggesting stuff or getting support etc I've set up a discord that I've done a frankly appalling job of promoting -> https://discord.gg/4YgkhAgfJ5


BTW you can also follow along on Reddit if you'd prefer doing it that way -> https://www.reddit.com/r/RadiantApp/


I love this! I did something similar recently with Phoenix10.1 (https://github.com/pncnmnp/phoenix10.1).


I love the idea, and I instantly downloaded the app. After a peppy welcome message from the robot, it doesn't actually play any songs. Just crashes constantly :(

I can send you any debug info if you like. But no pressure, it's free as far as I can see and I don't want you to worry just because it doesn't work for me.

Great idea anyhow!


Yep. That's not good... thanks for the offer, if you could shoot over an email to rad@getradiant.app and I'll get whatever broken fixed this weekend and released by Monday.


Just downloaded. I loved JackFM back when I listened to terrestrial radio in the car - it was a station with a snarky robot dj and it was great. Thanks for making this!


Is there like a link to a JackFM broadcast on Youtube or something? I'm super curious to learn what their formatting was like and maybe use it as a case study!


It was 100.3 KJKK Jack FM which I’m realizing was only in the DFW area. I figured it was syndicated

Here’s a link to what I’m guessing is their site: https://jack.fm/listen-to-jack-fm/

Here’s a YouTube video which is either a recording or a fan-made version. Either way the quip by Jack after the first song (~3:37) nails the tone for the robo dj’s persona: https://youtu.be/ewDE2rrRbH8


Was definitely syndicated. Listed to a lot in Southern California. Haven’t heard it in years though. They had the largest selection of songs.


oh wow thanks!


I think this is a really cool idea and you should keep working on this. You're onto something. Incorporate more day to day? Include podcasts that I subscribe to as programs? So much potential.


Short-form podcasts are being looked at as sort of a syndicated content. Like there'd be a list of interesting shows like 'The Daily', 'Business Wars Daily' etc that you could subscribe to and have injected into the stream when appropriate!

Obviously, I'd expand this with more full-fledged shows if people liked the format. You could even configure it with "I listen to my podcasts in the morning / after noon / when I'm driving" etc in settings and Rad would factor that in when choosing when to play em.


I would love to be able to listen to news podcasts in this.


> Why do it?

Doing stuff like this is how you get experience in areas where your day job may not provide you the opportunity.

After all - employers don't care how you got the skills, that you have the skills.


Also having something I'm passionate about gives me a lot of purpose. I've obviously up-skilled tremendously building (and then rebuilding it for cross-platform) but above all else, it's a lot of fun to build and it's something I personally wanted to see in the world and enjoy using!


I've been listening for about 30 minutes and it's pretty neat, I've already found some new music I like. However, the weather forecast told me it was 275° F.


Damn it! Thought I'd fixed this. Back to that micro service I go :(

Thanks for using and for the bug report!


Trying it now and it seems really nice! I wish you had a desktop/web version, and it would be my daily background radio while I work all day. Spotify's Discover Weekly playlists are nice enough, but they barely carry me through the first 1-2 days, and then it gets pretty repetitive.

It would also work really well as an Alexa skill, especially with Rad's commentary.

What did you write the apps in?


Yep, the idea is that the stream of music it plays is both time appropriate and always relatively fresh. You can tune its selection algo too with the thumbs up or down (long pressing on either for more fine controls).

Web is due out in the next 2 weeks. Alexa skill has been on the roadmap forever as I've always seen smart speakers as like the place it makes the most sense.

The apps are Svelte based with capacitor (planning on switching to Tauri when that gets proper mobile support) and some custom plugins for the native stuff. It was a native iOS app but got a full rewrite to support Android and iOS with the web planned as a fast follow.


Very cool! Joined your Discord server. Even if you don't want to monetize it right now, you should set up a Patreon or something like that, and at least let people chip in on your server costs.

It would be a very cool community-supported smart radio service :)


The app has a built-in link to 'Buy me a coffee' (which actually does cover my coffee expenses along with some of the hosting costs!)

I'm quite keen to get a bigger community of people contributing ideas and maybe give me the push to move away from Spotify.

Eventually, swathes of the service could go open source too if the community wanted it.

Thanks for joining the discord!


Looks like those clowns in Congress did it again! What a bunch of clowns.


Rad literally says this


Ha! How does he keep up with the news like that?


This sounds absolutely incredible. Definitely checking this out.


I had this idea myself but never bothered to make anything of it. Thanks for saving me the effort!


This is super cool, but the first thing I wanted to do was cast it to the Chromecast plugged into my hi-fi. It seems casting isn't available yet - do you have plans to add it? It would make this a total winner for just playing music in the background.


Chromecast support is a gigantic pain to implement! But I 100% agree it'd be excellent to have it!

Maybe it's gotten easier since I last checked in on it


Very cool, I've daydreamed about building something similar but always convinced myself I'd have to wait until text-to-speech was better to really incorporate all the sources I'd like. Awesome work!


The major advancements in text-to-speech we've since in the last year have me planning on revamping Rad's voice (maybe basing it on Tom Sellek...who knows) but the fact we've come this far has really opened a world of opportunities for audio-first experiences.


You could use unreal speech for this. Not a plug but i found it really cheap to make realistic tts using an api using it.

https://unrealspeech.com/


This looks (or sounds, rather) exceptional.

Long term I'm going to go with something self-hosted using Tortoise TTS etc but I also want to break away from Google's Cloud Speech as that can cost me hundreds a month when the user base has a peak so this looks great, thank you!


I’d be very interested to see what’s possible taking SOTA models and trying to get some version of them working offline, on-device.


Cool! Just signed up. I was a little turned off by how much access you need to Spotify. Is that just because they don't have granular enough permissions?


I know it's a bit of a laundry list. Everything there is required to use the Spotify API the way I needed to. Playlist read/write so it can add songs you like to the 'Liked on Radiant on Spotify', Profile to set your locale when making requests and for setting your profile picture if you have one etc etc.

I'll look at paring it back in future if I can!


It makes sense what you ask for based on what the app does! I was just wondering if it was an issue with scoping and them not providing enough granularity.


FWIW, I think you meant to say "paring it back" and not "pairing it back".

https://dictionary.cambridge.org/us/dictionary/english/pare


What does it request? That part was in french for me.


Basically write access to playlists and change access. I totally get why, I was just wondering if their scopes were limited.


Weird its in french. Thats all controlled by Spotify which suggests your Spotify is set to french. Might be worth checking to see if your Spotify is being accessed anywhere else...


Is it possible to onboard service onto Apple Music?


Not today but we're planning some radical changes to the music data we rely upon which should open it up to Apple Music, Deezer and beyond!


Got my attention! Switched to Deezer a while back and there aren't a ton of integrations for it. Which is fine, but also, they'd be nice.

IMHO, this is exactly the sort of functionality I'd expect to be built into any music service when I say "start song radio". They misuse the word "radio" by so many degrees, they just mean "shuffle".

Even if it's not broadcast over actual radio, at least give me an announcer! And you've done that, and I'm very intrigued. Is there a place I can sign up for reminders to learn when the Deezer connector is ready?


If you head over to our Discord which you can find here -> https://discord.gg/4YgkhAgfJ5 and it'll be announced there :)

You can also follow updates on Reddit -> https://www.reddit.com/r/RadiantApp/


I love it! And I would love to have some kind of Home Assistant integration so Rad can wake me up with news in the morning.


This is absolutely on the roadmap!


Thank you so much to everyone for the points and really nice words of encouragement. Real shot in the arm and means a great deal.


Downloaded, will test it, looks very promising. Absolutelty willing to donate. Do you take donations?


The bottom of the settings screen has a 'buy me a coffee' link but I'm equally happy if you're using it and enjoying it!

Or if you have feature requests please send them my way! Those are worth an awful lot :)


Thanks! I had some issues with playback as soon as the app was im background. The song switched but it did not start to play.


Very cool. An alarm function would be nice. Waking up with Rad! My family is blown away by the idea.


Interesting! I've never actually thought about that! Very clever!

If it was launched from the alarm it could start the show with "Gooood morning, looks like it's going to be <insert weather> and <insert some info about traffic on your usual route>, now let's get to the reason we're both here; great tunes." or something.


Public transport info for those of us that live in countries with good APIs for this stuff that travel in, too.

A long time ago I had an internet radio (musicpal) that played shoutcast stations, you could point the screen at RSS feeds; it felt kind of futuristic to have info on when my next train to work was on it, this would even more so.


I'd buy that for a dollar!


Just to let you know, on Android the "Connect with Spotify" button opens a Google Chrome view, which is weird, because my default browser for everything is Firefox.


It would be nice if you could make the DJ a bit more like the ones in GTA radios, in particular Vice City. I would pay for that!


This is literally my dream for the service. A personal GTA radio station. I'm entirely all ears if you have any suggestions on how to pull that off!


ChatGPT

> Write a Grand Theft Auto Vice City in-game radio advertisement.

> "Attention all Vice City residents! Are you looking for a new ride to cruise the streets in style? Look no further than auto dealership, "Tommy's Auto Sales"! We've got a wide selection of sleek sports cars, rugged off-road vehicles, and everything in between. Plus, with our no questions asked policy, you won't have to worry about where you got the money to pay for it. And for a limited time only, take advantage of our special offer: steal any car on the lot and bring it to us, we'll give you a substantial discount. So what are you waiting for? Head on down to Tommy's Auto Sales and step up your ride today!"


Ahh so fake ads! That'd be neat actually! Going to work on that over the weekend :) TY


I wish I could get the Mr. Sticky Buddy ads from the original YDKJ....

Chalky the Squirrel!


This is fantastic


I love the idea!


This is... awesome! Great concept!


Well, that was an easy sell.


This is very comfy.


Everyone Draw: https://everyonedraw.com

I created a little experiment a few years ago to see what would happen if anyone in the world could draw pixel by pixel on an infinite, shared canvas.

It has attracted a small community of fans who use it to relax and practice their drawing skills. The community has spawned some breathtaking pieces of collaborative art, including a world map[1], a galaxy[2], and a magic forest[3].

There have been a few donations, but not nearly enough to cover all my costs. I'm fine running it at a loss while I have a job. This summer I plan to take some time off from full-time employment to travel the world, at which point I'll try to monetize this project to cover my travel expenses.

[1] https://everyonedraw.com/1/-2564/-759

[2] https://everyonedraw.com/2/9339/-7770

[3] https://everyonedraw.com/1/40117/-40


You can sell loot boxes that contain different colors. Also sell finishing coats by the pixel. Once applied and dried (moderation) the underlying pixels can no longer removed.


Please don't do this.


Sounds like the million dollar web page where you just buy pixels for $1.


This is awesome! I love these sorts of creative community projects. Have you had to deal with trolls at all and how have you managed that?


Oh, absolutely. The initial launch was a disaster because I had no way of dealing with trolls. I've learned a lot since then, and built a bunch of tools that moderators can use to clean up the damage caused by trolls.


Can you share more about what you learned about moderation?


I learned how crucial moderation is for a community site like this. I originally hoped that the "good" users would overpower the trolls and create a self-sustaining community without any deliberate moderation. I was very wrong. I knew there were some people on the internet who like drawing penises and swastikas, but I totally underestimated the volume of these people.

I also learned the importance of bringing on additional help. I naively thought I could do everything myself (and I still like flying solo on the development side), but bringing on a volunteer to help moderate the site and manage the community has been incredibly helpful.


I played around with this for a while, and then realized it polluted my browser history with hundreds of entries. Please don't save a new history state every time the canvas moves. It would be easy enough to get rid of on desktop, but I'm not on desktop; the only way to remove these is to select them all individually and delete.


I built something similar for Android called Pixmap, which is a live collaborative drawing app. It was one of my first side projects! It's still online, only costs me like $25/mo to run, so...

You can also create private rooms etc.

There is also a competitive drawing aspect where you're shown an image and have to redraw it, and a matchmaking system with ranking...


Are these examples just different locations on the same canvas?


Isn't this a copy of Reddit's April fools /r/pixel game?


r/pixel was like the 7th iteration of this idea on the web.


The oldest one I can remember is million dollar homepage.


which is a copy of a copy, what's old is new


How do you deal with graffiti?


Graffiti is part of the fun!


Love it!


https://guestrevenue.com/ - an tool to integrate Airbnb bookings into Xero for short let owners who want really precise accounts. Built for myself, turned into a multi-tenant app because in 2019 it would definitely make me rich.

I have one user called Todd. He seems lovely but I don't have the heart to charge him because then he'd expect it to work. Everyone else has bounced off because they are weak. Actually I might have more users who just never got in touch; I haven't checked, but I'm pretty sure it can't be abused for Bitcoin mining. Maybe Todd is just the strongest of them - he doesn't mind downloading CSVs and trimming off the rows that cause mysterious 500 errors. It's a test of character. Maybe it is being used for Bitcoin mining and works anyway?

I maintain it because it's a lot less painful than typing 300 bookings a year manually, but a lot more painful than if someone else would just do it for me. It's probably not a business, but if you disagree you can have it for £100,000 - a high multiple you say - but you can't put a price on potential.


:D this is great


I run Plain Text Sports (https://plaintextsports.com/).

I got sick of waiting for ESPN to load so I made a site with the goal of providing immediate access to what people actually care about: sports scores.

It's pretty fully featured at this point, supporting the NFL, NBA, MLB, NHL, MLS, Premier League and Champions League, college basketball and college football, WNBA, NWSL, and the World Cup. And for a lot of leagues it has full schedules and standings as well.

It actually was really popular in South Africa during the World Cup when a "super-app" that points users to sites that don't use a lot of data linked to it.

The site is served off of S3 (which is cheap), but there's a job running on an AWS server that's fetching the data for all the games and republishing pages to S3. It's using Ruby and is making a lot of network requests, so it's definitely not super efficient. I need a least a couple virtual CPUs, so it ends up costing ~$60 a month. I could definitely reduce that number, but the trouble just isn't worth it to me right now.

I don't want to make money on it. It's been difficult enough to get people to use it; getting people to pay for it would be even hard. At this point I feel like I've gotten everything I've wanted from the project. (An eye-opening experience into the marketing world; a website that I use every day.)

I try to limit how much I work on it now to mostly just maintenance work. I'd rather work on other stuff. If I started making money that'd just be a number to obsess over, and, honestly, it's never going to make enough money to replace my salary as a software engineer.


This is cool, really dig the text look. Reminds me of https://wttr.in/. I would love to see more of these text-based sites.


I use it every MLB season and love it! Thank you for your work. Baseball is the perfect sport to go plain text, it already works really well over the radio etc.


Where do you get the data?


Really love the site. Is there a way to view multiple football/soccer leagues (i.e. Premier League (PL) and Champions League (CL)) at once?

I know you said you're just maintaining the website, but if there were a simple way to follow a team, that would be a really nice QOL addition. That way I could follow a PL team and see their CL matches as well without having to switch between pages on the website to make sure I don't miss a match. Perhaps adding the team as an URL parameter could keep the design simple?

If you want to take it to the next logical step, there are more leagues that a football club can compete in such as the FA Cup and Europa League. This of course is Europe-centric.


The intention is to put the schedules for everything on this page:

https://plaintextsports.com/premier-league/2022-2023/clubs/l...

The challenge is that these pages are really labor intensive, because I want to show relevant information for whatever league is happening, e.g., group stage points, leg of Champions League matches, and it's really difficult to figure out how to fit everything in just 45 columns.

I complained about it in this tweet: https://twitter.com/CodeIsTheEnd/status/1569489636900347904


This was a life saver when I was traveling in Europe and had limited data to use! Thanks for making and keeping it running.


In similar spirite, when the world cup was going on I used https://worldcup.cole.ws/ a lot to check on it. Much better than all other sites.


I've been using your site daily during the MLB season, the design is perfect. If you displayed a plain text advertisement I wouldn't even mind.


That is an awesome site that I will be using a LOT from now on! I love it when I find gems like this on HN! Thank you for making this!


Love the site. How can I contact you (I don’t have Twitter)? Would love to purchase the ability to use your code for our company!


I use this site every day. Thank you for making it!


Awesome. Could you please add the Bundesliga?


This is super cool


Love this!


PoachMe.Dev: https://www.poachme.dev/#/devLand?reqCode=HNGOBRRR

Premise: Recruiters spam left and right, so we decided to create a website just so they could get a familiar calendar-like interface but asked them to pay for your time. As soon as we exposed the external version with the URL, we decided to make an automated template ("Great. Please book a slot on my calendar and we can chat more about this. You'll receive my resume upon confirmation of the booking. https://bk.poachme.dev/Lazaro"). After that we ended up creating a virtual business card service so that could easily create a web presence without going through a different service (https://bk.poachme.dev/kBMf).

Availability: Web

Price: $0

Cost: Nearly nothing, it just sits with my other hosted services.

Why do it? Honestly, asking someone to pay for your time is the easiest way to see who values your time. The cost to send a single spam message to thousands of developers is nearly zero and it takes time to sort through the messages to see if there's anything good. I have had experiences going from blackmail all the way to people disclosing the actual salary for the position without any money exchanging hands which proves that when your time has value it's suddenly possible for the pay bracket for a position to appear.


I really like this idea, where I'm from recruiters are the absolute worst.. Being that this is your app can you disclose that the model works? Like are people making some money with this? I'd hate to take this line and get no bites, or worse alienate myself from the opportunities.

Edit: I just remembered the title of the thread :), I guess not?


> get no bites, or worse alienate myself from the opportunities.

Each person can do it however they see fit. I tend to use it as a way to get the critical info needed (company name, salary, remote or not). Recruiters who send me messages with enough info don't get a link from me. If you're still reluctant to give me enough info to make a decision can book at $100/hr, and about 5% of those book.

It's up to you, if you're getting shitty recruiters, send me them the link.


Great idea, you must pursue it. I too get a lot of recruiter spam. The idea should be extended to companies who take up several hours of your time to interview only to reject you. Life is short.


The same ideals apply to companies...

"Here's my booking link"


Followed the 1st link in post, used GitHub sign-up button, allowed pop-up, signed in to GH, authorized app, ended up on white page with message about missing session status or something (sorry, I didn't capture verbatim message).

Went back to 1st page and tried again. No GH login prompt, white page with coloured progress bar at top, ended up back on initial page with message "Unable to establish a connection with the popup. It may have been blocked by the browser".

Firefox on Android. (Btw, perhaps it's on purpose, but I can't select and copy text on that page.)


Sorry, man, things be on fire over here... I didn't think anyone would actually sign up.

Gonna check this out and see what's wrong.


Some feedback (not sure if this is on purpose):

I'm using Brave, and I couldn't right-click to "Suggest a Strong Password" in your signup field. I've never had that happen with any other site before. No adblock or Shields up.

Also I can't seem to confirm my membership.


Weird, I have never seen that dropdown option but I was able to do it (but I also sometimes get a "Suggest Password" option).

We're mostly developer focused so that email/password signup is really for non-github users. I'll check it out.


Mm, okay. I tried signing up (I'm a marketing/community guy) and didn't use the Github sign-up. When I click the verification email link it just hangs on your logo.


That's no bueno but we are getting the HN hug of death.

I see your account is created and ready to roll.


How many users do you have right now?

Last year I created a prototype of something very similar, the key difference was that the idea was to auto pre screen recruiters instead of ask for pay.


We stopped counting after a bit but regularly get an influx get new features drop (like the virtual business card) and when we post someplace.

It's profitable enough to cover hosting but honestly we built the features we wanted out a product we wanted and it went from there.


Reminds me of 21 Co's Earn Product RE pay for answering message


Goes to show nothing is truly unique in this world.

We mostly just got fed up with spending hours on interviews where recruiters showed up late or just ghosted only to realize nothing materialized.


Go Transit: https://gotransitapp.com/

I've built and maintain website + iOS + Android apps for public transit for several small municipalities that don't have a good solution. I usually end up adding cities if I visit there and an unhappy with their app offering.

Most of these municipalities use a smaller 3rd party vendor for tracking their buses, but often, the user facing application is sorely lacking. My applications utilize the same data, but try to:

1. Have a simple interface for quickly tracking buses 2. Have a simple interface to see times at your stops 3. Be specific to the city/transit agency. Most of the 3rd party vendors don't white label their apps, so somehow you have to know to download the My Stop app for Birmingham, AL, even though searching the App Store for Birmingham won't bring that app up. Once you have the app, you then have to find your transit agency.

Currently, I support Availtec, RouteShout, and TransLoc.

This was originally built for me in Birmingham, and I slowly expanded it as I visited other cities.


Just a friendly heads up, but Go Transit is also the name of the regional transit system in Southern Ontario, Canada (originally named GO Transit for Government of Ontario Transit, as it started as a part of the Ontario Ministry of Transportation). Calling it out because your app looks cool, but with the direct overlap in name and product focus, it could lead to a future trademark dispute if your app takes off.

https://www.gotransit.com/

https://en.wikipedia.org/wiki/GO_Transit


Yeah, I know. However, I white label all the applications, so the app ends up being called "Go Birmingham", "Go Steamboat", "Go Grand Rapids", etc... My users rarely actually find https://gotransitapp.com, and typically just search for City + transit on the app store.


Do google maps / apple maps / transit / citimapper / moveit not work for these cities?


Typically they do not. The Agencies _might_ submit GTFS data, but rarely do any of these vendors provide real time data in GTFS-RT that Google/App and other would need.

I find commercial apps like transit and moveit are only willing to work with bigger cities, and have very little interest in smaller agencies.


Interesting! Have you considered reaching out to one of those (e.g. Citymapper) and see if they would like to work with you? Either employ you, subcontract you, use you as an API, or whatever! :)

I think it's really cool that you maintain such a service and maybe they can find in you a good partnership!


I tried with Moovit, but they weren't interested unless the Agency was formerly part of it. At the time I was a board member on the citizens' board which was an official board of the agency, but still didn't have enough sway. The reality is that most transit smaller agencies are so under funded and under staffed, they just don't have the resources. Your lucky if there is more than one planner and a single technical person in many of these agencies.

I was the original person to create GTFS data (before real time tracking data existed, just stops, routes, and schedules) for my transit agency back in the mid 2000s, but again, Google wouldn't accept them unless they had signed agreements with the transit Agency. So at that time, I hosted my own Open Trip Planner instance.


One more thing I'll point out, is that I am reusing data that already exists for my apps. Most agencies are recognizing how important it is to have a GPS tracker on every bus. In some cases, it isn't for the rider, but is more for the agency to plan and keep track performance.

So, I am not the source of truth, which means any 3rd party app should really be getting their data from the original vendor. It is just a shame that many of these smaller vendors want to keep the data to themselves, and aren't willing to have public GTFS-rt data or data that other commercial applications are willing to use.


A bit of an unfortunate naming/seo clash as GO Transit is the public transit service in Ontario Canada.

https://www.gotransit.com/en/


How many users have you gotten so far? Looks really nice!


Awesome work!


https://thoriumsim.com

A multiplayer spaceship bridge simulator game, where your crew each takes a different position on a futuristic spaceship, explore space, meet aliens, complete missions, and hopefully keep your ship in one piece!

If you've ever played Artemis, Empty Epsilon, Starship Horizons, Star Trek: Bridge Crew, heck even SpaceTeam, this is in the same genre. It's pretty much Space DnD, with the option to have a Game Master role.

Still under development, but by the time its done it'll have a 3D universe simulation, crew and ship systems simulation, interactive controls for a whole bridge of friends, and an interactive mission designer.

I've got a handful of donations coming in through OpenCollective, but I just about break even with my hosting and Apple Developer program costs.


Glad you're still working on this, Alex! Keep it going


How do I play it? Clone the gh repo?


You can build it from the source on Github, or download the latest alpha release here: https://github.com/Thorium-Sim/thorium-nova/releases/tag/v1....

I've got a quick demo of the current alpha here on YouTube: https://www.youtube.com/watch?v=li51J9c1Wpo


Download a release. They're right there.


https://codeatlas.dev - codebase visualisation tool

Takes your git repo and generates a beautiful visual representation of the code. Sort of an alternative navigation tool (in addition to IDEs) for large codebases. Can also run it as part of CI with our Github Action (https://github.com/codeatlasHQ/codebase-visualizer-action).

We made this because grokking complex software projects is really difficult and we've found that a visual overview of what's in a codebase can be quite helpful to get started.

E.g. checkout https://codeatlas.dev/gallery/kubernetes/kubernetes for the generated visualisation of the Kubernetes Github repo!

Currently making -10$/year to pay for the domain :D We slowed down active development after our initial attempts at dissemination didn't really go anywhere (bragging about side projects on the internet, ugh), but I'm still really keen on getting some feedback on whether this is actually useful to anyone else!

Note: The site works somewhat on mobile, but is much better on desktop!

Also, funny there's a post like this again, just like https://news.ycombinator.com/item?id=34531989 yesterday.


Very cool! You could probably sell some kind of low-effort physical product, similar to: https://shop.lasertweets.co/. I bet there's some folks who would appreciate the coasters of their favorite repos.

Or, even lower effort, sell nicely-formatted digital prints of the repositories, so folks could hang them in their office.


Looks like this would be great for analyzing Yandex leak


https://www.twitch.tv/watchmeforever - AI-generated (aside from the artwork) parody of '90s sitcoms, running forever (24/7/365).

We worked on this w/ a very small team for the past four years, in-between our day jobs. When started, OpenAI didn't have an API, and Stable Diffusion definitely wasn't a thing, so we had to come up with novel methods to thread cohesive content together. Most of the "creative" details e.g., laugh track, dialogue, frequency of dialogue, camera shots, and so on, are all tunable on a per scene basis.

We're in sort of a holding pattern right now -- no clear path to monetization for the project, and it hasn't garnered enough attention for us to probably get funding based on the technology backbone. Hope you enjoy it! Labor of love. :)

(posted this in the similar thread yesterday but I’ll take any exposure I can get…!)


I couldn't figure out how to link the comment, but it was at least 9 months ago I said this, and someone was already working on it?? SUPER cool!

I feel like AI/ML and some pre-rigged models could be used to build a web-hosted sitcom. It would take a lot of technical work, and a lot of writing chops to make it watchable, but it could be done.

Look at Space Ghost: Coast to Coast, a show that was made by reusing old animations. If someone writes a script (use humans for now), then the AI/ML can stitch together the animation.

Once there's a corpus of material, start letting the AI determine plot points, and have humans vet and write it. Over time, let the AI take more and more control over the direction of the show, making sure to introduce new characters or events as needed.


I think you rightfully pointed out the "watchable" criteria. This is where we got to with 4 years of working on-and-off on it. The hard part is continuing to iterate over the structure to make it passable as a sitcom. The easy part is actually the language model stuff... we have an OpenAI integration, I just don't keep it on because it's a lot of $$$. We have lots of ideas about how to expand the show's structure, but it's mostly backend work that we simply don't have the resources to finish right now.

Luckily, our "goal" with this project was for it be nonsensical (hence the parody part), but I'd love to spin off a new show that focused on making it watchable for hours at a time. Our system is extensible enough that it wouldn't be hard to pop in new art assets and have a brand-new show in a month or two.


How do you generate your dialogue? Is it tuned as "conversation between characters", or was the model fed sitcom scripts?


Saw some articles about this and see you have 10k viewers right now - any clue where this burst of attention is coming from, or did this comment do it?


Oh lord, this is delightfully odd.

I believe some generate slapped bass licks interspersed would be nice. S*****d’s signature bass licks were actually played on a synth keyboard. Ideally the Melodie’s would be even more odd and sometimes go for very long stretches, always referencing the previous luck but elaborating on it in an annoying free jazz sort of way.


This is very unsettling to watch (a compliment)


This is hilarious! cool idea!


How do you do the dithering?


Jobs with Pride: https://www.JobsWithPride.com

Premise: Handpicked jobs from LGBTQ+ friendly companies.

It's a curated job board of the best jobs for our queer community, using publicly available information to source jobs at confirmed LGBTQ+ friendly companies - Verified by our 100% LGBTQ+ team.

Availability: Web

Price: $0 (Paid packages are available)

Cost to me: ~$100 per month

Why do it? - Finding jobs at LGBTQ+ friendly companies is hard, clunky, and time consuming - More than a 3rd of LGBTQ+ people feel they need to hide who they are at work - 1 in 3 employers won’t hire a Trans person - The LGBTQ+ community has kept me alive before, this is a small way I can payback the love


This might sound dumb, but aren't most corproate employers completely accepting of LGBT people these days (well, LGB people at least)?

What makes one company LGBT friendly and another not?


If only that was the case, specific industries are far worse than others as you'd imagine. Anti-LGBTQ+ rhetoric is also currently growing in the United States.

As far as the definition of "friendly" is concerned, that is a spectrum so I imagine we need the creator to respond.


Oh, I can definitely imagine issues being a gay man on a construction site, or something like that.

What sort of professional industries are homophobic, though? Genuinely asking, not trying to disagree or minimise what you're saying.


This discussion should probably be much, much longer... but I'll give you my take based on my experience as a queer person having worked in MANY industries from service to technology to government to private to recruiting/hiring to consultancy ad nauseum.

Generally it's not an industry or company that is homophobic but a person. This is why we have created nondiscrimination policies to protect from unlawful termination. It can be illegal, based on where you live, to fire someone based on Sexual Orientation or Gender Identity, but there are unfortunately many ways to subvert those rules.

93% of all Fortune 500 have a Sexual Orientation Nondiscrimination Policies, I'd say that's pretty good but that's only for Sexual Orientation. As you move down in revenue below the wealthiest companies, they are less nondiscrimination policies in place. Even some companies that claim to be LGBTQ+ friendly. So you can see why someone who has grown as a pariah and then later accepted by the majority of companies (because duh, money) would be skeptical of any company protecting their livelihood.

That is only one example of how a company can be LGBTQ+ friendly, another one that comes to mind is partner benefits (permission to attend company functions, relocation expenses, etc.). I personally have been prevented from attending a company dinner with my partner.

Again, this is just my take and I don't speak for everyone but I'm really happy to see a Job Board like this!


>I personally have been prevented from attending a company dinner with my partner.

Wow, that's insane. I'm not even sure that would be legal here in Melbourne.


Gay marriage only became legal in Melbourne in 2017. Completely legal to say that only spouses are invited to company functions.


If it's generally not a company that is homophobic then how can some companies be LGBQ freindly?


Some companies actively enforce their rules on discrimination and/or bullying due to homophobia, some turn a blind eye.


This is great, thank you.


Keep Close Friends: https://keepclosefriends.com

One day I noticed I was slowly losing touch with old friends - I moved, we all have busy lives and don't hang out just by chance any more. Those people used to be loved ones and now I wasn't sure. It felt like grief.

So I built a simple website where I can list relationships and ideal meeting frequency (say, 2-3 times a year), then get a few relationship stats and a reminder when it's time to reach out again.

I see it as a reminder that my life is short, and I like that. No other users yet but it feels right to try to help share that perspective around, for those who might want it.


do you really not have any subscribers? seems like this is making more than $0 :)


Thanks, I try to make it look nice! I started building it this Christmas and this HN thread brought the first users apart from my girlfriend and brother. All on free trial, we're 17 now!


When attempting to register on Firefox Mobile, the register button doesn't do anything. With all data filled in.


Thanks for reporting. I'm on Firefox android and can't reproduce. No sentry error so I assume the front is not sending the request.

The email is an 'email' field and apparently firefox mobile will block sending if the email is invalid (missing @, ...) without showing any warning, is the email standard?

(Other obvious steps: is it still happening after a refresh, the stack is vueJS (+ laravel/inertia) so I assume you have JS enabled already? ublock shouldn't be an issue.)


Disclaimer: This project isn't currently publicly available.

I was using Simple as my primary bank, and their Goals feature made it possible to do envelope-style budgeting really conveniently. Unfortunately the bank that backed them, BBVA, sold to PNC. This lead to my Simple being shut down, and my account was converted first to a BBVA account and then to a PNC account.

When I lost access to the Simple app I first built myself a spreadsheet, and then started work on a webapp called Complex to replicate their functionality. Currently you have to enter all transactions manually, but I eventually plan to integrate with Plaid so I can automatically pull in transaction data. Without automatic transaction imports, I'd say Complex currently falls about halfway between the original Simple app and a spreadsheet in terms of convenience/ease-of-use.

I don't have any kind of business model for this, but if I eventually make it public I'll probably charge a monthly fee to allow automatic transaction imports so I can cover Plaid's fees. There's not much server load required to run something like this, so I expect I'll be able to keep server costs below $20/month even if I pick up a couple hundred active users.


I won't use Plaid to connect bank accounts so entering transactions manually would be my use-case. There are some of us out there. :)


You'd be competing with the likes of YNAB, that provide a lot of features already today (including auto-import in most countries). Tough job.


YNAB is $100/year and though it is polished and well-designed, it's a pretty simple system that hasn't changed much recently. I think there's a lot of room to compete on price, particularly for users like me who still enter all of their transactions manually.


YNAB is too much hassle


yeah I also don't want any third party getting ahold of my transaction data. My solution was to have my banks send alert emails to me for any transaction. Then the alert emails are forwarded to a Dockerized email server I set up. The transaction data is automatically parsed out of the emails and loaded into a database. The only cost for me is the server.

Honestly the email server could be gotten rid of if someone was willing to directly access their gmail email account via IMAP, or whoever you use for email. I thought it would be a fun challenge to make an email server x_x

My goal is to make it so people like you could write some regex for their bank alert email parsing, spin this up, and be off to the races with no third party interference.

Here's the repo (WIP): https://github.com/katefike/sage


Check out Finta.io it’s a nice simple service by a solo hacker and could be a great partner. She wraps Plaid and streams it to popular destinations like Sheets and Coda, where users are given some starter content in their account and are free to go from there. Check it out, the connector is slick, but the budgeting and analysis tools aren’t there yet.


Share your email somewhere, or send me one (cf profile). I'm working on an app which you could be interested in :)


Have you seen https://dasbudget.com

It's a near clone of the Simple interface with new enhancements like CC Integration. Currently active in the App Stores. Web App is coming soon. uses Plaid and MX for integration


Man I miss Simple. I'm honestly shocked and saddened that nothing took its place, though they were a major pain about getting my wife an account so we could join finances and then they closed a few months after I switched away.


A Plaid developer account is free and will let you connect to up to 5 bank accounts.


It's 5 by default, but you can actually connect up to 100 accounts for free if you submit a request for full development access.


Yes, but it also comes with giving Plaid all the data and history about your bank account transactions.


Have you heard of the Lunchmoney app? I found it recently and find it to be a nice in-between of spreadsheet and full automated budget app. Plus it pulls transactions in


created an account here just to say i would pay for this service if it worked near real time. my wife and i were so bummed when simple went away and we haven't found a bank or service yet that feels like it provides the same feature set effectively.


another person who was crushed by simple going away and would love to pay for something like this!


CoolModFiles: https://coolmodfiles.com/ (just awaiting sponsorships)

CoolModFiles is a web player that will introduce you to the most obscure and legendary tracks hosted on the internet's biggest module archive, modarchive.org!

The web player works by simply fetching a random module from modarchive.org and playing it. No black magic involved!

The idea for CoolModFiles originated among two programmer friends who used to send mod files to each other, which lead to the creation of a personal mod archive - one which had hundreds of cool modules at the time! Being in possession of those rare works of art (all the way from 80s!) was a privilege... When the awesome tracks started piling up, however, it naturally brought about a storage problem. The solution was simple: using a web archive!

The programmer friends' idea, unfortunately, was beaten by modarchive.org many years ago. Realizing how unnecessary creating another internet archive was, the project evolved into a cool web player instead. A group of 3 came together to create what is known today as CoolModFiles.com. With it's modern look, it continues to surface thousands of long-forgotten mod files to introduce newer generations to the world of old-school digital music.


> fetching a random module

Ow, yeah, but a lot of 'em are really lame.

I'd love a setting for like "x% of plays should be in the top Y% of popularity" to guarantee some bangers every now and then. Or the bottom, if you're just 2kool4us.

To introduce someone new to the format, say, 100% of plays should be in the top 5%, melt their face off and then let 'em explore the obscure stuff later.


>The programmer friends' idea, unfortunately, was beaten by modarchive.org many years ago.

Sorry about that :-) Glad the API has come I handy though, your thing looks very nice, but “mobile bad desktop good”? Get with the times ;)


Nice work, I hope you find that sponsorship!

Feature request: button/key to randomly swap through those awesome backgrounds :)


I love that interface. <3


Great!


AWESOME


This isn't public yet, and almost feels like the kind of thing I'll never ship.

I've been working for a while now on the idea of a card / board game. The concept was bouncing around in my head for a while, and I started taking a lot more notes on the idea after my second kid was born (4mos ago). All of a sudden, I had a lot of time to sit quietly in a dark room with my laptop (and help the kiddo get to sleep). I eventually came up with a list of ~200 cards for the game, about 4 different decks, all stored in a big-ol spreadsheet I'd been editing on my phone (as I pace to get him to sleep).

But eventually with the idea, I kind of got it as far as I could with my mind's eye, and had to start actually playtesting. That would be practically impossible for me. There just isn't the time in my life right now to set up a small board game, play through it, take notes, and iterate on the balance.

So what did I do? I took that spreadsheet, dumped it to JSON, wrote a script to convert the JSON to placeholder .pngs of each card, and then built a dummy webapp with a canvas to simulate a virtual tabletop. Yes, I could have used TTS or something similar, but I felt the inner loop of changing the stats for cards, re-exporting them, then removing them and re-adding them wouldn't scale well.

This has ended up working great! I've been able to play through my game 20+ times now, all with a sleeping baby in my arms. I don't need to worry about leaving the game out on the table (for the 2 year old to find) - it's all just saved on my laptop. I don't need to futz with re-printing cards any time I want to change things, I just edit the "database" and reload.

I finally feel happy enough with the balance to show friends and family, which I thought would be a pipe dream just 3 months ago.


Stumbled on someone's workflow for creating AI cards/tabletop materials using stable diffusion: https://www.youtube.com/watch?v=fsTQY3VMJ78

Might be interesting to you for playtesting when you want to show to others! Good luck on the game - I'm a big tabletop/board game nerd, so would love to play it once you get the game ready!


Holy GOD that's way better than anything I have. I'm definitely gonna follow that, thanks for the link.

Ultimately, I'd want to have the art _not_ AI generated, but for the sake of prototyping, I could care less :)


For playtesting, this might be helpful: https://boardgamelab.app/


You should post a screenshot of this!

I'm also impressed you're able to edit while dealing with a fussy baby; I find it impossible to be productive on a smartphone, and my son wouldn't go to sleep if I was standing at my workstation (keyboard noises and the screen are too interesting).


It's a very careful balance haha. I mostly just do spreadsheet updates on my phone at this point. I've got a very delicately balanced laptop next to the rocking chair, so I basically use a pillow to support the baby in one arm, and work with the other.

It's been an _incredibly_ slow process, as you might imagine :p


* slowly chants in the background *

ship-it-ship-it-ship-it-ship-it!


<3

Maybe I'll make a writeup and post it to HN. That's the least I could do haha


Funny, I did almost the exact same thing for a MTG app I’ve been working on, and similarly also started messing with the idea of using the same software to soft launch my own rtcg. I would be very interested to see how you did yours.


Honestly, I would almost rather _not_ share the code, because it's Bad. Like, I just have one big <canvas> element and redraw all the entities (cards, tokens, etc) anytime there's input. It's got terrible performance for being what it is.

I'd kinda rather that no one in their right mind copy what I did.


Nobody.live: https://nobody.live/

Filterable interface for finding streamers with zero (or one, for StreamLabs etc.) viewers. Surprisingly intimate, in my opinion.

I run it at (little) cost but got some solid coverage: https://www.pcgamer.com/this-website-only-shows-you-twitch-s....


This is just so wholesome. I love it. And that's gotta be a cool thing for someone to randomly get a viewer. I know when I randomly stream (only when I play MSFS...), it's really cool to get even one viewer! (It's usually zero)

It reminds me of a similar site for YouTube awhile back that would show you videos with zero views[1].

[1] http://www.petittube.com/


https://www.bootstrapsite.com

I've been working on a Bootstrap 5 landing page builder for almost 1 year now (mostly just weekends though).

It's like my pet project than any money earning business but it gives me pleasure to work on it so I just keep at it.

My plan is to open source it soon so people can create their sites and landing pages for free and host it on their own servers. Initially I made it create my own sites and learn Vue 3 but I'm kinda hooked on how it's turning out to be.

Right now everything is free including ssl hosting. Maybe to support the hosting cost I will charge a one time fees later on, but except a small "Powered by blurb" there will never be any difference between paid and free plan.

It's work in progress so I don't think it's ready for a Show HN just yet but that's the next big thing on my list.

The main USP of this builder is it's targeted more for developers and people who know what Bootstrap 5 is than just another website builder (need to update the landing page to reflect that soon).

If anyone has 5 minutes to spare and want to play with it I would really appreciate your good honest feedback about the builder and everything. No signup or cc is needed for trying by the way.


Looks pretty cool, one thing that would be nice is the ability to delete, copy, and paste from the canvas. Also on trying to signup with my email I got a server error followed by a message that my email already exist.


> would be nice is the ability to delete, copy, and paste from the canvas

Yes it's possible. Please see this image

https://imgur.com/a/zgnmF0E

> Also on trying to signup with my email I got a server error

Yes the server error was due to SES not being able to send emails (fixed now) but the account was created.

Thanks for the feedback


I am definitely going to try this now.


I have been looking for something like this.

I will play with it over the weekend and I will ping you my feedback.


This should be a regular feature on HN, somewhat akin to "Who's hiring?" and "Who wants to be hired?". Maybe not on a monthly basis, but it would be cool to see periodically on some cadence.

There's a lot I could say on this topic, but TBH, I don't want to go into most of it in detail Right Now for various reasons. The main reason being simply that the side project stuff I might want to call attention to is largely not in the state where I'd want people looking at it right this minute. And the reasons for that, in turn, are manifold...

The good news is, progress is being made, and I should have some projects ready to put "out there" kinda soon'ish. Yay for being vague, I know. But I've learned to be leery of making hard promises on stuff like this. So much shit happens that you can't control. See above about "manifold reasons".

Anyway, we're not making any money yet... in fact, we've been losing money since day one, but thankfully the amount lost is relatively small since our expenses are small. Nothing that I can't just pay out of my $DAYJOB salary.

All of that notwithstanding, if you want a somewhat outdated view of what I've been working on for a while, see:

http://fogbeam.github.io/

https://www.fogbeam.com/

If things go well, this year will see lots of improvements to the underlying projects, videos, blog entries, and tutorials explaining how to use everything, and entirely new stuff not shown at the above links - as well as finally having everything available in SaaS form.

Sadly my backlog of "ideas to implement" remains far larger than my bandwidth for implementing stuff, so FSM only knows if/when some of the stuff I want to do will ever see the light of day.

NOTE: the "demo" links you may find if you click through the above links are offline at the moment. I'm in the middle of a big infrastructure migration / automation effort; moving a lot of stuff from Linode and "other" to OVH, consolidating DNS at Route 53, automating deployments with Ansible, etc. And one thing that hasn't been done yet is to bring up the new demo server(s).


What is your audience for this? I'll be blunt: I have no idea why I should pitch this enterprise thing to my boss.


Yeah, the material that's out there right now doesn't do a good job of explaining the uses for this stuff. I had, at one time, gotten pretty decent at giving the pitch F2F and had it down in my head pretty good, but I doubt I could do it justice now. Part of the problem here being exactly that a lot of this stuff has lain largely dormant for a few years now due to external forces. Back when I was actively trying to sell the stuff to people, we had some interest from some people, and probably would have had some revenue already if A. I were more of a natural salesperson and B. I didn't have a heart-attack at an inopportune time.

That said, I totally hear you. There's going to be a lot of stuff coming to better articulate the vision of how this stuff can be used and how it delivers value.

To answer your question though:

What is your audience for this?

For what is really the core of the vision:

"Large companies (where we still need to refine exactly what the threshold defining 'large' is) with many disparate IT systems who want a more unified "knowledge layer" on top of all of those disparate systems, such that they can find content without having to jump from system to system so much, find useful connections between disparate bits of knowledge, and manage actions associated with content".

The genesis of all of this was an observation I had years ago, which somehow amazingly seems to still be true, that pretty much all enterprise search solution are a shit-show, and coupled with a belief that "social" tooling (things similar to FB, Reddit, etc.) can be useful tools in an organizational setting. Add semantic web tech to the mix, and I think there's a way to build a much better KM solution.

Now, pretend I just said all of that 10 or 15 years ago. It would have sounded better then. One unfortunate aspect of how all of this has played out is that the world has moved on in some ways. Things where we had interest a decade+ ago won't seem particularly novel now. But the key, I believe, is that many of those ideas still hold value even without being "cutting edge" anymore. The upside, if there is any, is that at one point some of the stuff we were talking about was actually pretty innovative, so the Rest Of The World has caught up to us, but perhaps not too much more. The "knowledge graph" stuff in particular is something that people are still talking about. OTOH, "social" tooling in the enterprise is pretty passe now.

So where I'm at now is working to update all the "old stuff" from a tech currency standpoint, get everything back to a good stable place, and then start thinking more about what has to change (if anything!) to represent something we can sell in today's world.

Sorry for the long ramble. Not wanting to do just that is why I almost didn't post in this thread at all. I've said before that I could probably write a book about my experiences, and at this point I probably should. :-)


https://gif.so

Every subdomain gets its own gif, so you can query by url (i.e. https://hackernews.gif.so). Anyone can change the image that loads on a given page... one day I'll make it a voting system. Useful for quickly putting a gif of an arbitrary thing in chat apps as most will unfurl the image directly. If you just want a static image, use https://jpg.so instead.

Someone else made this years ago and hosted it at jpg.to. That went down a while ago and I recreated it because it is fun and sometimes useful and not owned by Meta.


Small bug I've noticed, with gboard keyboard when you select a suggestion the keyboard adds a space after.

So it'll input "dog smiling " and your website will give a 404.

A trim of trailing spaces should be an easy fix.

Thanks for this page, I find it much better at recommendations!


Can we do projects that we know will stay at $0 but we still hope might gain traction?

OSS: typed-graphql-builder https://typed-graphql-builder.spion.dev/ is a TypeScript based graphql query builder. No more writing untyped strings and running a watcher in the background - generate the builder from the server schema once then write any queries in TS with the help of the language server

It was inspired by tql (https://tql.dev/) but generates a much smaller client and has full, automatic type inference for query variables used in input objects.

(Side note: I feel bad about how similar it is to tql, but the code generation approach was so different (mainly inspired by graphql-zeus) that it felt like poor form to just send a PR changing everything.)


This is very neat, and I've actually been planning on building something similar - just never got around to it. I wasn't aware of tql, though, so it's not unlikely I would have just used that instead.

The only "downside" I can see is that all my projects are already set up to use graphql-codegen, and switching to this or tql would just not be worth the effort. This is because 1. it's really not that much of a hassle to run graphql-codegen on the side, since i'm already running other things on the side anyway 2. I'm also using graphql-codegen for other things, such as generating types for cache updates and such in urql.

I might give this a spin in a fresh project, though. But it probably won't let me drop the codegen dependency completely.


Having banged my head against the guilds graphql code gen tool for the past two days, I will pay you 10 in the am, if this thing works and you explain to me how the f to get their config file to read both schema and ops files.


I built an Hreflang testing tool. https://app.hreflang.org

Hreflang is an arcane SEO concept. If you have sites in different languages then you can tell Google/Bing that site.com/page.html and site.fr/page.html are basically the same page only in diff languages.

The way to specify this is using meta tags in your HTML, and it's quite complex and error-prone. My tool checks if you implemented this correctly. It's running on a VPS so my cost is quite low.


Holy schnikees, I learned something new today. Thanks!


Wanting to experiment with Shopify, I decided to make a t-shirt shop for cyberpunk and sci-fi stuff. So I registered a short sci-Fi sounding domain: https://hex7.org and proceeded to toil (many many mouse clicks) away stocking my shop with with hand-designed shirts and coffee cups and then waited.

2 years in, not a single sale :<

Partly I wanted just to add products and see if the combination of Shopify, Google, and my super-niche geeky products would generate at least one lonely customer… but no.

Did I buy ads? No. Did I SEO? No. Did I use ChatGPT to write tons of shitty Cyberpunk stories and blog them? BRB…


Thanks for sharing. I like! One of my own current side hustles involves creating and selling t-shirts, hoodies, caps, etc. just like you. And also like you, I had ZERO luck trying to sell them in my own store (Shopify, WooCommerce). However, when I listed them on popular DTG-type sites, they started selling, and now sell several hundred $ per month. I'm talking Teepublic, Redbubble, Spreadshirt, etc. I didn't initially want to go that route because I thought making $2 or $3 per shirt sounded pretty crappy when I could have my own store and maybe make $15-$25 per garment. And also have control over my client base. But hey, a few hundred $ per month at $2-3 per shirt profit is almost infinitely better than $ZERO per month at $20 profit. I dunno, maybe give it a try? :-)


Wow that’s amazing. Thanks


If you are interested, I'd also recommend that you check out Michael Essek's YouTube channel (no affiliation, just like his stuff). He is a very successful t-shirt designer who sells books and materials to help people design stuff like this, but he also dispenses a LOT of free advice on his YouTube channel, if you are lucky he'll even critique your design on his show and give you advice on how to improve! Check https://www.michaelessek.com/ or on YouTube at https://www.youtube.com/@MichaelEssek


I run a SaaS service for large POD merchants (basically, people doing what you're trying to do, many of whom are making a living at it).

Shopify does not give you organic traffic. You don't want to start with Shopify unless you already have a dedicated audience.

If you're just getting started, places like Redbubble and TeePublic are the easy way. Low margins, but it's "fire and forget". Amazon Merch used to be the hot ticket but it's pretty saturated. I would say that Etsy is the most popular place to make money in POD right now - it's a little more involved (you pay listing fees) but you control your pricing.

I've been in this space for about 6 years now. Happy to answer any questions.


Was going to say almost exactly the same thing. Etsy is a far better place to start for this kind of thing. Makes it easy to add some level of internal/external advertising as well to get started.


To be honest the t-shirts don't look that great. Maybe there is room for improvement.


FINALLY some product feedback!! What would make them better?


Maybe GP is not the target market and I guess I'm not either? The only thing that appeals to me at all is the hacking the Gibson poster. Pretty cool. I have zero idea what all the other stuff is, if there are references I don't get them and the designs aren't interesting enough to intrigue me.


Maybe it's not my style so take my opinion with a pinch of salt. Hal9000 and Ono Sendai design are too basic tbh. Broseph feels much better. Also the black color really feel like it's for teenager or maybe metal vibe people (could be the customers you're targeting?). Maybe try to show different tshirt color in the front page so we know there is more than just black. Try to add more design? All the best!


You have a sale. Maybe the most expensive mug I've ever bought :) I look forward to it.


Wow thanks Kevin! ;) now I am longer in the $0 club!


I just bought something too!


dunno if its just me, but i think a dark site would suit a cyberpunk theme better. the photos with the plant and chair don't look very cyberpunk either

the other thing i noticed is that the graphics on the main page are hard to see when on mobile. the graphics are small enough so when you include the models head in the photos then the graphics are even smaller. maybe the thumbnail/first photo could be zoomed in. threadless.com for example just crop at the models neck.

also, maybe if you could find stock photos of people that look more cyberpunk that might help


Is there a particular reason you didn't buy adspace?

I imagine it's the main way that most shopify stores make their sales, and is probably a good way to realise some gains from your time investment.


Have you heard of CyberDog, its a clothing brand in London


Do you supply a feed of your products to Google Shopping? It's free now.


Hmm how does that work?


https://typeracelive.com/

I wasn't satisfied with other type racing sites because they were not real time enough for me. I wanted to be able to see exactly where the other racers' cursors were and where they made errors.

I don't expect to make money any off of this, but it was fun to build and I find it fun to play with my friends every once in a while.

The stack is React and ChartJS in the FE (that's it), and Rust with Warp in the BE.


Really nice, I especially like the design of the stats.

One thing that throws me off quite a lot is the smooth cursor animation, good to see that you already allow to turn that off.


The website looks amazing! It's one of the nicest type racing website I've seen. :)


This is really well done. I completed it on my phone. I wonder what the gap between typing on a phone and keyboard are?

Anyway awesome project!


Not exactly my project, but I have been helping a friend of mine work on his pet project for the last couple of months: https://limeline.app/.

He currently makes no money from it and has no intent on making any anytime soon, hosting cost are pretty low and it was pretty much just created out of a need we both had: being able to aggregate all our sources for our morning technology watch.

In the end, with feedback from a couple of friends, he built a simple "no inbox" RSS aggregator with some nice extra features (account-less page management, sharing & forking of feeds, ...).

It is still in a pretty early stage, but I really like where this is going and feels like it deserve more visibility.


I just checked it out, very cool. Always wanted something like that.


I'm working on a TUI Jupyter Notebook editor, euporie, which allows you to run and edit Jupyter Notebooks in the terminal:

https://github.com/joouha/euporie

It's useful for editing and running notebooks on remote servers over SSH, or inside containers where setting up port forwarding is not possible or too difficult, or if you just like working in the terminal.

It's open-source, and I have no idea how I would go about monetizing it!

I've spent a lot of time recently working on euporie's HTML renderer, which I'm planning on using to make a new terminal web-browser.


Impressive. I started working on a similar project, it's a NodeJS debug environment embedding a console, a debugger, and network & performance analysis tools. A bit like the browser dev tools but in the terminal.

Hope mine will reach the same maturity someday!


This is incredibly cool. Unfortunately, I don't think it's something I would pay for. But the bit I tried out seems great! I like to live in the terminal and this seems like a nice way to keep doing so :)


I’m building https://polyglatte.com a language learning website (and app) for learning with real content like YouTube videos, subtitles, and text articles. Ideal for intermediate and advanced learners.

Some neat features are that we fully parse the text and part of speech tag it, we have a system to prepare for difficult articles/videos with clips from easier ones, and the core idea scales really well to more types of content like chat messages and images (not public yet).

Our focus is now shifting to on-boarding and marketing. We have a few users that have figured out how to really use Polyglatte and they love it and use it a lot but for the most part, many users leave without seeing most of the value we can provide.

It’s a self-funded 2 person project and we haven’t monetized it at all yet.

I have no problem charging for it but I need to figure out how to help people really understand the value we provide and reach more people before it would make sense to do so.


Wow! This is really cool, will definitely be using this for learning french. Thank you!

Just one question, is there a way to make words by default known? I’m at an intermediate level, and don’t really want to tell the program that I know all the rather simple words.. or does that not really matter?


Glad you're enjoying it!

Currently the best way is just that there's a "mark known" button at the bottom of articles to mark all remaining words as known. Also on the wordlist view you can select many words and mark them all known at once. But we're also working on integrations now to help make the on-boarding experience easier and leverage existing study workflows.

The main challenge is that in Polyglatte a word is defined as (lemma [the root word], part of speech, language) and most other systems don't use part of speech, so there's often not a 1 to 1 mapping when importing. So we've delayed having much here so far, but it is definitely a solvable problem. Is there a specific place/format you would want to import that data from? If not then perhaps we can add a "mark wordlist known" button and add some French word lists.

> I’m at an intermediate level, and don’t really want to tell the program that I know all the rather simple words.. or does that not really matter?

That's a good question, due to the way typical word frequency distributions are, the problem becomes less annoying pretty quickly if you mark words as you see them. But solving this problem is also an important part of making Polyglatte fun and a smooth experience for new users. And helping people to spend more time enjoying and using their languages is one of our major goals with Polyglatte -- bulk marking words you already know isn't very fun.

Feel free to reach out on Discord or our new community forum (https://community.polyglatte.com/) for help or for feature requests by the way -- we'd love to make Polyglatte better for you and everyone else.


Wordle Race: https://wordlerace.vercel.app/

Just built this to get more familiar with Real Time tech (Use Supabase under the hood). In this version you and your opponent race to get the word while being able to see each others moves! This way you can use each others words to gain advantage. :)

Would love for you all to try and appreciate any feedback. You can just create a room and invite anyone you want to play against.

I have a lot more (unprofitable sigh) side projects I keep at: https://www.hackyexperiments.com/


https://thechillypony.com

Allows you to configure a zip code and alert temp, and you'll get an email if the forecast temp falls below that alert temp, so you can know when you need to blanket your horses. Built it to scratch my own need. Makes $0 :)


I don't live in the US and don't have a horse, but I love this site. Such a simple site and a focused idea, it's refreshing.


Ha, interesting and simple site.


Holy Bible Study & Cross-Reference Tool: https://bible-ui.rkeplin.com/book/kjv/1/1

Also, Holy Bible Search & Cross-Reference API: https://www.rkeplin.com/the-holy-bible-open-source-rest-api/

Made 0$ so far :)


Nice! I did a few projects like this, but with more modest UIs:

- https://github.com/juliend2/data-bible , for french translations

- more recently: https://1mbible.co

Have you thought about using some AI techniques (like Word Embedding) for your search engine? I'm interested in toying with this a bit in my next Bible-related project.


Nice, - I like the simplicity of your UI. Though I can't read French, it looks like you've got some nice features there.

No, I haven't thought of thought of that. Very cool idea.

I'd like to make the API accessible via JS from all domains, but using an API token. I'm starting to get a lot of requests to use the API, however, most everyone wants to call the API directly via JS. Right now they have to go through a proxy like NGINX or some server side proxy.


Nice work. When I change the version after a search, it resets to Genesis. I think it should keep the search results.


Thanks, - yeah I agree thanks for catching that


https://github.com/DustinBrett/daedalOS

My passion project is building an OS in the browser. I've been at it for 2 years now. I've had interest from people who want to turn a profit with it, but I am happy to just keep adding features and polishing it forever.


This is impressive. If Firefox has resist fingerprinting config option enabled, timezone is forced to UTC. You may want to allow a custom offset.

https://support.mozilla.org/en-US/questions/1322612


This is really impressive!


It actually feels really polished!


I work on NES homebrew projects, mostly involving chiptune libraries that can be used to make games on the original hardware. I'm especially happy with the visualizers for turning musical creations into videos. I'd love to spend more time on it but I have to pay the bills, but still... figured I'd make good on the desire and try to turn it into a Patreon.

https://www.patreon.com/zeta0134

Here's like... pretty much all of those projects running in the browser at the same time: the music engine, the emulator, piano roll, and some of my own covers as demo tracks.

https://rusticnes.reploid.cafe/wasm/?cartridge=bhop-2a03.nes...

It's an extremely niche thing to even be into, and I'm very new to this whole self-marketing thing, so I'm still learning the ropes. Right now I don't make enough from my own patrons to offset the amount I happily pay each month to other creators. I enjoy the work on its own merits, so that's fine, but it would be great to one day connect with enough of an audience that I could justify spending more time on it than I already do.


Not sure if you know him, but there's Remute, an artist from Germany who does... hm... electronic music and publishes it on vinyl and most of the time in some kind of cartridge format (Hucards, Gameboy, SNES etc...)

Not sure if he's done anything for the NES yet...


3D dice rolling with friends https://dddice.com

Have some ideas on monetization in the future but for now it's just fun


Very cool! I'm curious: How did you render the 3d dice? What's the front end stack?


Thanks! Frontend stack is React, Three.js, and Cannon.js. We use FBX for the models mostly but started to support GLB files recently which open up a world of new options for customization.


This is dope! Whats the tech stack behind it if you don't mind me asking?


Thank you :)

Laravel, MySQL (Planetscale), Redis. Hosted on fly.io

Total monthly expenses is somewhere near $30/mo which is less than I've paid for personal hosting at times.


Very cool!


I have an open hardware project (libre, technically) to develop a solar powered phone. It's more of a concept, or a framework, rather than a list of components that I'm assembling outside of research. I would be more than happy if someone forked the idea and made something of it. https://hackaday.io/project/177716-the-libre-autarkic-laptop Anyone could manufacture it since the PCB, open cores (royalty free), blueprints and STL and PCB design would all be open sourced to anyone who wanted to make it, thus it encourages collaboration.


I'm not ready to show it off yet, but I'm working on a workout and nutrition tracking service.

No other tool or service out there matches the feature set I want so I decided I'd just build it.

My goal for workout tracking is mostly to make it crazy simple and super fast. As close to 0 barrier between you and your tracking. I want PRs to be more than just "moved a bigger amount of weight". I think volume PRs from rep records, etc are also important.

For nutrition tracking, I want the ability to save some commonly used foods to my local storage to make it faster.

I want discoverable meal planning. The plan is to basically let the user pick a protein, then a cooking style, which expands into different recipes and then side dishes to fit the remaining macros of a given individuals macro goals.

For calorie tracking, I think its important to display that weight change isnt a day by day thing. You need to look at the caloric deficit or surplus for the week or the month vs weight change to see how you are doing. Most other trackers just give you feedback day by day which doesn't really represent reality. They also don't automatically adjust your TDEE over time with weight change.

Not sure if anybody will pay for it, but I want it so I'm going to build it :)


A few years back I built a tool that pulled your data from MyFitnessPal and calculated a running TDEE for you, so that it was easy to adjust week to week. It was very useful to me and I managed to get somewhere in the range of 100 active users before I ended up moving on to other projects.

I say that to say good luck, I think your app will be useful!


LunaTrace: https://lunatrace.lunasec.io/

Premise: Open Source[0] alternative to GitHub Dependabot and `npm audit` that focuses on helping you prioritize where to patch first (since only 0.1% of CVEs are used in cyber attacks).

Short YouTube demo: https://www.youtube.com/watch?v=ugdSyR2L6sY

A newer video showing off the Static Analysis engine: https://www.youtube.com/watch?v=vPd4MSUJ98M

Price: $0 for Open Source repos. We're hoping to charge for private repos in the future, but we need to build out the billing features first lol. (We're at $0 in revenue currently.)

If you are filled with rage because of CVEs spamming you, come vent your frustrations on Discord: https://discord.gg/2EbHdAR5w7

We're looking for early customers that are interested in working with us. My email is on my profile. Cheers!

[0]: Source Code, https://github.com/lunasec-io/lunasec/


Looks awesome!


I made an App to help find out food intolerances. Basically make it super easy to enter what you have eaten. Not even based on individual items, just basic foods like soy, tomatoes, onions... help me figure out that it was garlic which was causing all the trouble.

https://app.foodolyst.creatness.studio [Web]

https://play.google.com/store/apps/details?id=studio.creatne... [Android]

Currently trying to release it on IOS, but Apple is very strict with these types of apps.


Ah great, I always wanted to do something similar. Will check it out.


https://www.budgetable.io/

This feels like the 3rd budgeting application post on here lol, but here we go.

A next-generation budgeting application, offering everything YNAB does, except at a lower price point, mobile application available (iOS & Android (soon)), plus with added features such as balance projection into the future as well as the ability to input fictional transactions and see outcome of those transactions on disposable income, etc.

Integrates with Plaid for banking, AI categorization and recurring transaction detection, auto-syncing transactions, the whole bunch.

I have a lot of features in the works to bring it much further than YNAB, although I think I already have feature parity. I don't have really much free money currently (saving for something big), so I don't really have much to allocate to marketing, so currently just spreading via word of mouth.

I really just made it as a budget replacement for myself, as I was running out of a google sheet which made it difficult to really use.


https://font2png.com to create PNGs from icon fonts like Font Awesome. SVGs are usually the way to go, but sometimes you need a PNG. A previous tool that did the same went away, so I built my own.

Also https://frt.rip, a whoopie cushion with spatial audio, because I had the domain lying around.

Both don't make money, but they also have no users besides myself so they can run on my cheap server for free basically.


> Also https://frt.rip, a whoopie cushion with spatial audio

This may be the most magnificent phrase I have ever read on the internet.

But when I visit in Firefox (mostly vanilla, on Pop!OS), a scary warning pops up that the site is trying to do something to my machine, with no context of what. I presume that "spatial audio" requires some support beyond just whatever my browser already knows how to do, but.... what?

Hey, it works with no warnings on my phone! Oh, and that audio is glorious. Juicy. Extravagant.

This is going on my smallest most concealable Bluetooth speaker...


Thanks. The spatial audio is just a feature of the excellent https://howlerjs.com/.

But I added MIDI keyboard support to the secret fart piano recently and thus Firefox throws up a scary warning. It's now disabled unless you access https://frt.rip#midi. But you can also use your computer keyboard to play/fart a little tune, see Web Inspector for instructions :)


> https://font2png.com to create PNGs from icon fonts like Font Awesome.

Would you consider an extra slider for the corner radius? That would allow to download icons with a background which is not completely square, but also a squircle or circle (maximum corder radius).


Alright, the background can now have rounded corners with smoothing / squircles like in iOS, using Figmas algorithm. Thanks for the suggestion! → https://font2png.com


Nice! Thank you for taking the request and for the fast turnaround.


Good idea. I never really use the background color, but since it's there, a corner radius makes sense. I'll play around with that soon.


I have a bunch of those.

https://writingstreak.io - a tool for developing a daily writing habit.

https://screenplays.io - a library of free screenplays.

https://startupideas.io - a newsletter where I research and analyze startup ideas, opportunities, and trends.

https://rpgadventures.io - a discord community where we a group of Game Masters brainstorm, create, and publish adventures for roleplaying games together.

https://improvgames.io - a discord community where I run free weekly improv workshops.


Ah I love this ask HN!

I'm building an iMessage app (www.pigeon.ooo - nothing here yet, I just get a hoot out of the name) that brings note taking into iMessage. I built it because I wanted to be able to save/pin messages so that I wouldn't have scroll up to find important pieces of info. You can also share the lists directly through iMessage so that the others in the conversation can update the notes, which has been particularly useful for grocery shopping lists and weekly planners with my S/O.

Currently working on a companion app so that I can view all notes not segregated by conversation, or ordered by due date etc.

It hasn't been publicly released yet but it will definitely be net negative. Doesn't matter though because it's useful to my friends and I plus has been fun to build.


You should add a clickable link. Also, it seems to just lead to a placeholder page as though it was just registered.

http://www.pigeon.ooo


Thank you! I would do if it wasn’t just the place holder page. I just like the domain name we chose, I have clarified in the original comment.


Is www.pigeon.ooo a typo? Doesn't seem to go anywhere


Nope! Nothing there yet, I just get a kick out of the domain and wanted to share it, even if a bit premature.


Doing that for decades.

An app for Windows phone, downloaded 140k times: https://github.com/Const-me/SkyFM

Cross-platform graphics library for .NET: https://github.com/Const-me/Vrmac

Recently, offline speech-to-text for Windows: https://github.com/Const-me/Whisper

At this point, I consider side projects like that as a hobby.


I just tried out your Whisper Windows port and it worked perfectly for what I was looking to do, thank you so much!


The whisper implementation is awesome. Thanks for creating it.


https://www.tabletopunglued.com/

This is a collection of original papercraft designs for helping people have fun playing D&D. It's a way for me to get some hobby time away from the screen and keyboard. All the designs are available as pay-what-you-want, most people pay zero, and anything that people do pay goes to me supporting other creators on DMsGuild.com.

Unlike most papercraft, these designs are meant to be pretty sturdy and useful rather than just decorative. Most are about as strong as an empty soda can, so you can handle them and toss them around or even stack a couple books on top without crushing them. And, the source diagrams are included, so you can customize the art.

If you check out the "About" page you will see that the purpose is to explore inclusive accessories for D&D that people can enjoy regardless of their disposable income, and with less environmental impact than typical plastic, wood, or leather accessories.

Also, each product page ends with a haiku.


initiative.sh[0], a web-based text interface for creative D&D play. After a promising response on HN[1], I had hoped that I might be able to monetize the project, but traffic has since crashed to almost nothing. I would say that after six months of full-time development it is about halfway to being complete as a freemium product, so instead I've opted to open-source it.[2]

It turns out that the challenge with launching a freemium product is that you need something that's both useful as a free tool while also having a compelling value-add for paid users. That's a lot for one person to build. I don't think I'll be aiming for that monetization strategy with future projects.

I have to confess that I'm (barely) missing the qualifying income bracket - some kind soul is supporting me for $5/mo on buymeacoffee.[3]

[0] https://initiative.sh/

[1] https://news.ycombinator.com/item?id=29106581

[2] https://github.com/initiative-sh/initiative.sh/

[3] https://www.buymeacoffee.com/initiative


Interesting idea. Might be able to pivot into a world-/knowledge-builder of sorts. Plug in gpt3 or Ai on the generating side; add links between nodes and graph visualization... And it could be useful not just as a GM tool, but for research for creative writing - or even for a wiki-like system (assuming another wiki-like mode for view edit).

I'll try and play with it to see if it fits me for writing a small campaign I'm starting.


Nice work! Saw your previous post about jumping to doing your own thing full time in 2021, kudos on shipping.


Thanks, I appreciate the support.


https://alive.is a service that checks if you’re alive and sends a message to a person you specify if you fail to it. I create it for myself, in case something happened to me while travelling alone to make sure my family would have all necessary information. The service encrypts the information on server-side and end to end and doesn’t store any historical data. Didn’t thought about monetization yet.


https://universe-dawn.com

a browser based mass multiplayer online game with a sci-fi "the expanse" like setting.

remember the old school (2004) games you used to play with your browser. play it again with new technology but old flair.

currently there are 150 players, but no money made so far because I don't like pay to win and without that it's hard to monetize such a game

I recently translated it into english so everyone can play with us :)


You can might be able to monetize by adding things like probabilities or in-game calculators. One of the early Facebook mmos I played had this, and I was happy to pay $5 a month until they decided to be p2w instead.


As a hobby project, I run Code::Stats[0]. It's a website that tracks what languages you are programming in (via editor plugins) and gives you a profile page with various statistics[1]. It's ad-supported (with EthicalAds) to deal with server costs, or you can buy a support account to remove ads. The site and all the editor plugins are open source, the site is written in Elixir (but I'm looking at integrating Gleam in the future).

Currently it's completely a free time thing; I make negative money on it. My dream would be to have enough paying users to work on it part time (even a little), but that's far away and may never happen. But I like using it myself so I'll keep running it for the foreseeable future.

[0] https://codestats.net/

[1] https://codestats.net/users/Nicd


I just saw this and as a project this looks great. But the more(maybe most) popular version of exactly this tool is Wakatime[0] and I've been using it for quite a while now. So my question here would be what "new" feature you plan to add to this so you can standout from other similar but popular services?

[0] https://wakatime.com/


Honestly, I don't know. I think WakaTime is great (based on what I've read), and it does time tracking which Code::Stats does not do (and probably will not do). Other than that, I don't really know its features because I've never used it, so I don't think in terms of how to compete with WakaTime. I just think of things that I'd like to see in my own service. I know people who use both, and why not?

Code::Stats started as my own version of an old site called Codeivate that had a similar XP based tracking system. Codeivate disappeared from the web completely for unknown reasons, so I launched my own because I liked the idea.

As for future ideas, one of the more requested things is user groups that would have combined statistics and internal leaderboards (with heavy disclaimers), so I'm definitely doing that at some point. I'd also like to do more gamification side things, like badges for reaching certain levels in languages. As a third, I want to look into monthly/annual reports that could be emailed.

If you have ideas, I'd love to hear them. :)


https://lilhash.com/ https://github.com/jackbow/lil-hash/

A simple temporary URL shortener that produces easily rememberable and speakable URLs. The links expire after 24 hours so there's always a one word shortening available. Receives approximately 20,000 visits each month.

Useful for sharing a link in a presentation, or between devices when you don't want to login to your email, etc. When its easier to remember or say a link than send it.

Fits in cloudflare workers free tier.


Would you consider selling this site?


hyperspace

https://hyperspace.so/

My 3rd attempt to reinvent the web platform around an open & easy-to-use core.

The idea is simple: what if HTML was the source of truth for web applications?

• Every app would be a front-end site that's remixable

• Anyone could copy a site and use the tools you built to help you change it to edit it themselves

• You could edit a site at any level of abstraction -- in the browser's devtools or with a site builder -- anyone could participate in the platform at the level they're comfortable

Still early days, but I have:

• CodeMirror/devtools editing

• Read-only backups on every save

• Quill.js plugin for content/blog editing

• Copying other people's sites

It's meant to be a no-consequences, lightweight way to make and share apps, ideas, and interactive sites (where every possibility fits into your head)


it sounds a lot like you're reinventing what Beaker Browser had built on top of DAT, except that it could do more. For example, they made a distributed Twitter clone as a proof of concept, but folks actually started using it. Definitely included blogging stuff.

Really cool stuff around taking sites and things other folks had built and using them as a basis for your new thing.

https://github.com/beakerbrowser/beaker/ If you're not familiar i'd recommend starting with some of the YouTube videos giving an overview. It was pretty cool.

Alas, the main dev was hired by BlueSky and is now working there... but wonders if maybe you couldn't take that idea or its tools, and mush it together with yours.


Hey that's me. Thanks for the shout out

@panphora yeah you're project looks like (IMO) a smarter version of what beaker was doing. Smarter because the p2p element ended up being a bit of a tech-fascination that got in the way. Hyperspace seems to be doing the actually-cool-UX of self-editing sites and then getting out of the way otherwise.

The beaker team made a distributed twitter clone, but the cooler one (Rotonde) was made by 100 rabbits and you "made your profile" by forking somebody else's profile It's messy but fun (the software itself is viral!).

If you create js apis for reading other sites and enumerating the files in them, you can get a lot of power out of that.


ngl it's pretty cool but I can't find a use case for it


What about a simple blog?


Any links to cool sites already made with this?


The home page is made with it :)

No cool sites made by users yet though, the creator (me) is still the only user haha


I'm developing calculang, a language for calculations: https://github.com/calculang/calculang

I've made some examples here: https://observablehq.com/collection/@declann/calculang

Some tooling work for visualizations and for showing the workings will be released in the next weeks.

There are no positive money flows; I've spent many years experimenting, developing, and now 1 year after a public release the twitter page where I make announcements has 24 followers: https://twitter.com/calculang

I'm a modelling consultant - I work with numbers, I think they should be simple, but they are disjointed across systems and entities and programming languages and spreadsheets. The friction accumulates everywhere: to get a simple result, to follow the workings, to do any analysis, to share one or the other. calculang can consolidate calculations/numbers and is also a tool for transparency, understanding, and education.

I haven't done introductory documentation beyond the technical README which I think is vague (feedback accepted), and I plan to do a Show HN introduction to the community when I fix key snags: documentation among them.

For me the project is rewarding on many levels. In my client work - mostly financial sector - there is usually limited scope to take a really fresh perspective. There are no restraints here, it is useful to broaden my interests and thoughts in modelling, visualization, and wider more-grounded things like education and transparency, and I also get to be enthusiastic about a project that's tangible and simple at its core. In other words, plenty of positive flows besides the direct $ number :)


Momenial https://momenial.com — a mobile app for creating certificates for webinar attendees.

Currently making $0/mo. I'm actually building this app as a "case study" for my upcoming book, an opinionated guide to building mobile apps, from ideation, dev, ops, and marketing. I've been blessed with working at various company sizes and wearing multiple hats: founder of two failed startups, VP Eng at a telco and a large retail conglomerate, and now CTO of a medium-sized fintech.

The book won't promote microservice, Kubernetes or anything Google-level. It's a modern-but-practical guide "for the rest of us". If this sounds interesting, please create an account in Momenial—I will send updates about the book there (because it doesn't have a landing page).


Strong concept. One of my clients does CE training and I currently have to create new PDF certificates whenever they create a new course or move info a new state. Have you thought about casting this as a simple API and charging devs like me for it? I would just pass along the cost to the client, maybe with a bit of a markup. Or maybe even better (for you), I'd instruct the client to bank $10 at a time with you (recharge their account) and maybe that would allow me to generate 100 certs (or whatever makes sense here) before they have to recharge and deposit more.


Bulwark Passkey: https://bulwark.id

It is an open source passkey manager that allows you to export your passkey credentials in an open format. I built it because I think passkeys are much better than passwords, but all the currently proposed solutions (like Apple and Google) lock your login credentials to the device, which is a non-starter for me.

It doesn't make any money, but I personally wanted it to exist, so now it exists. I'm hoping that it will help open source passkeys to take off.


I work on a Python game engine called Arcade[1] and other projects within it's Github organization such as pytiled-parser. We also help to drive continued development and improvement within Pyglet[2]. Recently, my efforts have been focused on creating a version which can be run in web browsers by using Pyodide and WebGL[3], though that is still fairly early stages.

Arcade's primary focus is on being an educational tool for beginner programmers, so my hope is that with browser compatibility we can lower the barrier to entry further and make it more accessible and easy to get started with. In a similar vein to the goals of browser compatibility, we've recently enabled full compatibility with Raspberry Pi through the use of OpenGL ES(and this was largely only possible thanks to the huge amount of work that everyone involved in the Mesa project puts in)

I'm not the original author of Arcade, but I am a current maintainer and put a substantial amount of time into it and it's community.

[1] - https://github.com/pythonarcade/arcade [2] - https://github.com/pyglet/pyglet [3] - https://github.com/pythonarcade/arcade-web


I've made a bunch of projects that hit about 80% completion that I never end up finishing. My current projects that I have most recently put in some time are:

https://cruisedirector.io/ I have it running on some of my sites. It continues to run but I have no customers, and I haven't tried to sell it as a service. Tracks user actions inside an application. Every click is tracked so you can make rules based on any user clicks and show prompts made with a graphical editor. For example: Someone is button smashing, you can ask them for feedback. Popup a message on first login in the past month... Really lots of fun stuff.

https://ezdataloader.com/ I recompiled some old c# code from about 10 years ago, and with a few tweeks the backend now can run in mac, windows, or linux. Pretty sweet, other than the interface. I used electron for an interface and got it working a bit. But, I haven't put too much time into this one either. I'm tempted to scrap the downloadable executable, and turn it into a saas app. Might be a bit easier for customers I'm targeting. I've been pretty busy at my day job though, and haven't had time for this in the past year or so.


https://spotify.smithy.dev/

Built it in a few hours in 2021, my girlfriend and I have a collaborative Spotify playlist, and as everyone knows Spotifys shuffle feature sucks. When on a road trip we'd constantly have the same songs play while on shuffle mode, so I built this, it basically just does a Fisher–Yates shuffle on a selected playlist and allows you to save this new order back to the playlist on Spotify (non destructive on Spotify, which unfortunately means an API call per song order change). Now no need to use Spotifys shuffle! Its worked well for us, we actually get a properly random playlist order.

Price: €0 Cost to me: Like €7 a month for a VPS than runs other stuff as well.


An open source Deno starter template that includes session handling and e2e Puppeteer testing that runs on Github Actions:

https://fresh-strapi.deno.dev/ https://github.com/Hyprtxt/fresh-strapi.deno.dev/actions

And this site uses the sessions and e2e testing, but not Strapi: https://videopoker.academy/ https://github.com/Hyprtxt/videopoker.academy


Sheetmailer: https://sheetmailer.io/

It allows users to create personalized emails from the data in an Excel sheet. They write a template like

   Hello {Name}
   Your grade of todays exam was {Grade}.
   Best regards
   Prof. X
The mailer automatically fills out the gaps with the corresponding column of the Excel sheet.

Since it's been running, I got a single one-time payment (about four years ago). I'm using it a lot myself though.

Luckily, it's almost free to run (on a 13$/m Hetzner machine, shared with about 10 other applications). And as a teacher, I used it to send over 4000 emails containing grades and similar stuff to my students.


If you could include a generated PDF using the same simple template concept which gets attached to an (also templated) e-mail and ensure the e-mail isn't flagged as spam, and doesn't cost 60 dollars per user or some other such nonsense, I promise you there is a market for this. Big market.


Automatically replacing text in PDFs is not easy sadly. The problem is that the text doesn't automatically reflow if a long text is inserted. What exact application do you have in mind? It might be possible to use a Word file as a template, and automatically generate a personalized PDF from that.


You interested in selling this?


Automated Python utility to collect Zaptec EV charger usage and invoice details. Calculates a price per kWh and sends an invoice to the registered charger user using a third-party invoice solution.

Zaptec has a decent API. Invoice retrieval (electricity) and invoice distribution is done by faking browser sessions with Python.

I live within a housing association (townhouses) where the garages are separate from the houses. All chargers are on the same fuse box.

Commercial solutions providing the same service are typically $5/month for each user plus a 0.01USD fee for each kWh. I figured I could save myself and my neighbors some money.

Currently hosted on GitHub, but private repo as I am not too proud of my 3 evening rushed code.


NoraSector: https://app.norasector.com/ -- real-time police/fire/EMS scanner for the Seattle area. Uses custom SDR software that can capture entire radio systems and streams with sub-second latency to clients, along with recordings.

For all sorts of reasons I decided not to monetize it. I've had some inquiries to use it for newsrooms and in certain states that have laws that require radio traffic be published online. I explored some of that but could never come to agreement on a price that would be worth my time to support. I also considered monetizing with ads and having a premium membership, but it's a little too niche and expanding to more regions requires more investment than I'm willing to make.

King County is migrating to a new digital system in the near future, and if they encrypt everything then it's dead in the water anyway.

Costs me about $200/mo in hosting fees to run, plus about $1400 for the machine/SDR that captures the radio traffic. I use it myself and don't mind sharing it with the handful of people who listen to it. If/when the access is cut off, I'll shut it down.


I spent a large part of 2022 building an async p2p networking library for Python. The main reason I wanted to do this was because years ago I tried to write a similar library and it didn't go well. So yeah: I wanted to see if I'd be able to do it any better with my current software skills. It was really important to me that I finished something for once, too.

I worked hard on the project and I do feel that every aspect has been a significant improvement from what I tried to build in the past. It really makes me appreciate just how much sacrifice it takes to build good software. Like you can't be lazy and just be like 'yeah... this kind of works so the code stays.' I had to re-write code multiple times. I lost track of the number of re-writes for some of the more complex modules.

I will also say the most significant reason the project ended up successful was due to an emphasis on testing. I spent months writing a test suite and increasing 'code coverage.' In doing this I found many problems and re-wrote code until it worked how it was supposed to. My emphasis on testing is what ultimately made the software in any way stable enough to use. Where ever possible -- live testing was used with real infrastructure so I know all features work in the real world.

The software is on Github and Pypi: https://github.com/robertsdotpm/p2pd https://pypi.org/project/p2pd/

Taking a brief break from the project to recharge. So if you find a bug it probably won't be patched right away.


PeaceFounder: https://peacefounder.org

For the past few years, I have been exploring the idea of building an e-voting system around the anonymisation of voters rather than votes. In contrast to existing systems, the design enables the publication of all election evidence, verifying the legitimacy of the votes without sacrificing either privacy or transparency. Election administrators only need to take care of server identification secrets. It does all complex ElGamal re-encryption mixing before elections without the voters' active participation by simply shifting a relative generator on which voters would cast votes. This would make the Price/Security for running elections small compared to what is already out there.

Currently, the project is in a heavy development stage. I have settled on making a microservice which would be easily integrable into existing systems allowing members to enrol for voting by simply scanning a QR code. At the same time, the admins would be free to choose how they want to present data. REST API for the user and server, which onboards users, is now finalised. Now I am working on UX for the client application and, hopefully, will start to code a prototype in GTK in the coming weeks.

http://htmlpreview.github.io/?https://github.com/PeaceFounde...

The feeling is much like playing a game of chess with oneself. Trying to finish it while I am young and can still keep the scope of the problem in my mind. If anyone is interested, I do enjoy a friendly argument ;)


I've spent the past two years or so working on Tachi (https://bokutachi.xyz/) (https://github.com/TNG-Dev/Tachi), which is a modular tool for tracking rhythm game scores.

Generally, everyone was using their own personal spreadsheets or ancient "just render everything" tables to analyse their scores and progress before this and I'm pretty happy with how it's turned out.

What I'm probably most proud of is that adding support for a new game is adding a new module for it - all of the other features automatically work with it. This turns a "each game needs to have its own full-site tracker" into a "each game needs a configuration for this one tracker", not unlike how LSP simplifies adding language support for editors!

Taught me almost everything I know about scaling a codebase, and despite being a niche tool it's picked up a lot of momentum (2k users, ~3m scores).


Simplest File Renamer - batch rename files with your favorite text editor (and see the diff of the changes)

https://yboris.dev/renamer/ -- FREE

MIT Open Source: https://github.com/whyboris/Simplest-File-Renamer


I need this thanks


My works over the years are accumulated on https://www.nayuki.io/ . Lately I finished writing a new PNG library ( https://www.nayuki.io/page/png-library ), and now I'm revamping a DEFLATE library ( https://www.nayuki.io/page/deflate-library-java ).


Do I need an Umbrella Today?

https://umbrellatoday.app

The idea has emerged from my personal frustration with having to carry an umbrella (large or small). Large umbrellas are heavy and cumbersome to carry, and are often lost at events, while small umbrellas provide insufficient protection and are prone to breaking. The conclusion is that there is a need to minimize interactions with umbrellas as much as possible, and therefore we need a simple yes/no answer before leaving our premises.


It looks pretty good, I’ve been looking for something like it. Though in my case I want to know of full days. I.e. I want an alert for “will it rain at all tomorrow”? When checking the current day, it’d be useful to see all hours of the day and if it’s going to rain in any.


Thanks for the feedback! Something that is similar to what you are mentioning, is the setting “How many hours should we look ahead?” which can be found when you click on “More” during the setup of the alert. Then it will give you per 3 hours the forecast. Cheers!


https://conservationhub.nz/ - Very likely not applicable to anyone here because it's a very specific target market but I've been working on a platform that helps conservation groups in New Zealand record field data and work with local volunteers.

A lot of conservation groups in New Zealand have a similar problem where they need to record their data on-site for bird monitoring, trapping, etc to get funding. Some went and built their own apps to achieve this, but I noticed the groups that did ending up spending tens of thousands building essentially the same thing with minor differences in the data captured. For a while I helped groups get set up on a low budget with existing tools but none were really customizable or intuitive enough for volunteers recording their data and admins managing that, so we ended up creating a web/mobile app for it instead.


I built https://courses.so.

The concept: build courses with Notion.

The idea came from my partner in the project, who runs an e-learning community centered around no-code tools and wanted something simple and no-code-y to host their material.

I built it during a bad main-project burnout day and we've been improving and marketing it ever since.

We have a bunch of people using the free plan to publish their courses for free, but not enough users pay the 9€/month plan, which allows you to charge for the courses, to pay for the infra.

So we're in the negative monthly profit.

Still, it's a fun side project and we enjoy improving it and listening to user feedback.

If you want to offer or sell courses and you like Notion, check it out. Especially if you are a maker type, we offer API access and are working on full access to statistics and event webhooks so you can integrate it with your systems. We even have first party integrations with Zapier and Make.com.


Geoquest: https://geoquest.wout.space/

It's a geography game focussed on learning all countries in the world.

Had it online for about a year now. It's completely opensource [1]. Only accept donations through buymeacoffee, no ads, no paid version.

I don't spend any money on it as it's hosted on Cloudflare Pages and all data is stored offline in localstorage.

[1] https://github.com/woutdp/geoquest


Very nice indeed!


Semantic Paint will be a system for annotating text that does not rely on filenames or URL's or any other naming system. Instead it uses fuzzy hashes to identify where in the text to attach the annotation. If you peer your node with other people, you'll see their annotations too.

It's like the web, except you don't need permission to create links between data, and whether you see other people's links/data depends on whether you explicitly subscribe to their "brushstrokes" in that "color".

"Colors" might include:

- this-javascript-is-malicious-and-here-is-a-patch-that-neuters-it

- this-is-a-claim-and-here-is-evidence-for-it

- the-food-described-by-this-menu-entry-causes-allergic-reactions-for-people-with-this-kind-of-allergy

Ideally, users (or aggregations thereof) will emerge as authorities on these topics and we can figure out how to pay them for being useful curators.

Since the references (this and here in the above example) are anchored to other pieces of text by CTPHs and not by name, you can find text in the world and point your camera at it and now you have links to follow.

There's a mapping between CTPH identified text and cryptographic-hash identified text, so we can use a DHT to move content around, I'll probably have plugins for different network constraints (i.e. Bittorrent, IPFS, Freenet, SSB, etc).

Since I'm solving the hard problem of naming things by just not naming things, I don't need an always-available DNS server (for instance), so I might as well see what else I can do without. I'm shooting for partition tolerant and latency tolerant, to run over secure sucttlebutt protocol (which presumes that the user is moving around gossips over ad-hoc networks), so it can be useful in a world where the ISP's are unusable for some reason.


I run a ton of things! The one I work on most right now is International Persuasion Machines: https://ipm-corporation.com/

The product, as it is right now, is a battery of tests of different browser configurations used by bot-makers, targeted at a URL, and then a ton of measurement around the cost of different theoretical implementations, which implementations are able to get through to a site, common themes among current working attacks, and how far into your stack bad requests might get. As an example, here's a scan of Kelley Blue Book, which I imagine tons of scrapers hit regularly: https://vulnerability-assessor.ipm-corporation.com/dashboard...


Thank you for this thead!

I am currently working on a new open-source project, completely free to help enterprise manage their authorizations on a ce realized application: https://www.authz.fr/

Main benefits whereas existing projects is the simplicity of use and the frontend web UI which is generally in paid offers.

It comes with Service Development Kits in multiple languages (Go, NodeJS, PHP, Python) and more to come soon.

I hope someone could find something interesting here :)


https://qwerty-fr.org/

Note: This keyboard layout is not just about English/French anymore. You can now type pretty much every latin language in the world: Spanish, Portuguese, Irish, German, Italian, Català, Dutch, Danish, Flemish, Swedish, Norwegian, Finnish, Czech, Polish, Romanian, Lithuanian, Serb, and many more but my fingers are already hurting.

Now… Time for the sales pitch!

~~~~~~~~~

Are you tired of the limitations and inconvenience of the AZERTY keyboard layout when trying to type in French? Introducing QWERTY-fr, the ultimate keyboard layout for French and English language users! This layout is based on the widely used QWERTY layout, but with added symbols and diacritics to make typing in French easy and fast. Plus, it's easy to learn! With QWERTY-fr, you'll no longer have to rely on autocorrect to fix the shortcomings of AZERTY.

QWERTY-fr also eliminates the frustrating letter swaps and shuffled symbols of AZERTY, making software shortcuts and remapping a thing of the past. Plus, you'll be able to type special characters like "É" and "Ç" with ease.

Our layout follows a strict superset of the QWERTY layout, meaning all keys are in the same location, so QWERTY users can easily transition to QWERTY-fr. To type special characters with diacritics, there are simple rules to follow. AltGr corresponds to Option on macOS and Ctrl Alt on Windows. With AltGr and the corresponding letter, you can type characters like the grave accent, acute accent, circumflex, diaeresis, cedilla, and ligature.

So why settle for the limitations of AZERTY when you can have the best of both worlds with QWERTY-fr? Try it out online without installing it and join our Telegram community to discuss and provide feedback with other users. Don't miss out on this game-changing keyboard layout!

(Courtesy of ChatGPT.)


Watchflix: https://watchflix.group

I made this extension to watch stuff together with my girlfriend during the pandemic. All the other extensions had a lot of flaws, didn't work with Prime and Disney+ Hotstar, so I decided to build one for my own use. I moved to the same city as my partner, so I don't have any use for it anymore. Few people still use this daily, so I'll probably let it run on my VPS as long as I can.


You might be able to eliminate the VPS by making it P2P using something like PeerJS [1]. PeerJS provides a free shared connection broker server.

[1]: https://peerjs.com/


https://payload.app/ is a cross platform desktop LAN file transfer app with drag and drop UI, directory support, resumability, e2ee, and auto discovery. It’s designed to be easy to use, fast and ephemeral. My philosophy is to take transfer seriously, as opposed to hosting and sharing (which in my purist mind should be treated separately, and has less overlap than people think).


My friend and I have been working on a replacement for Facebook events in our social circle. We found that a lot of people are not using FB events anymore and were having a hard time planning social events. Not making any money (yet) but we hope to someday! We designed our app to make it easy to share invites on any social platform/chat group without being tied down.

https://dateit.io


Look nice. Can someone with a dumb phone and internet on a computer use it ?


Thanks! Yeah we support iOS, web and android! We are still adding support on web to create events but you can view and respond.


how did you launch this? to your existing social circle/friends or did you do any marketing?


We started with our friends and family. We have been running ads on the App and Play store. Nothing too crazy. We are starting to look into more local advertising to drum up interest!


Drive Declutter: https://drivedeclutter.com ,

A snappy disk visualization tool for Windows 10/11 similar to DaisyDisk on MacOS. Developed in C++ from scratch without any frameworks, whole download is about 3 megabytes. A few hundred downloads and much fewer sales, it's currently a free download everywhere except for USA, where it costs a few bucks after a 24 hour trial. Downloadable directly from the Microsoft Store: https://apps.microsoft.com/store/detail/drive-declutter/9P54...

It's only making beer money but I enjoy maintaining it and adding features over time.


Music Tonight: https://musictonightapp.com/

Makes a Spotify playlist of artists playing near you, tonight.

No revenue. I really just made it for me; make the playlist in the am, listen during the day, and maybe see something that night.


Honestly this does a better job of letting me know who is playing nearby than any other event advertising I've seen. I have no idea who these people are near me today, but now I get to sample and discover them. I actually just bought a ticket for a small show at a school near me that I never would have known of otherwise. I dunno if you're into making money off of this but it's the sort of idea that has some legs. Thanks!


A little encouragement goes such a long way. Thank you for trying it out, and especially for coming back here to let me know how it went!


This is really cool. I don't use Spotify so I'm curious if there are any plans for branching it out to other services like Apple Music?

At any rate, I've shared it with some friends that do use Spotify and they all love it.


Oh, thank you! I don't have any plans for expanding to other music services. But skimming the Apple Music API, I think it's possible. Particularly if you think you'd use it, I'll investigate a bit more and let you know. :)


Valar: https://valar.dev

It's kinda like a private SaaS platform. I just run it for me and a couple of friends right now and just hosting a ton of little fun side projects on it.

e.g. https://tim-efa.valar.app which brings Munich's public transport schedule to your terminal (try it with curl, looks way better)

It supports all kinds of things like bring-your-own-domain, e.g. I run my portfolio page https://espe.tech on top of it. It is partly open-source (actually only the CLI for now) but I plan to fully open-source it in the future after cleaning up the code a bit and improving testing and stuff :)


https://tvdatanow.co/

We're an Ad Tech startup - cross device attribution measurement aimed at CTV specifically... and we have very few clients, just enough to pay the server bills and expenses but not enough to actually pay ourselves. Been like this for 3 years now.

It's hard, because the job is fairly demanding and it takes effort to keep this kind of big data apparatus going, but at the same time it's never quite dead and almost just barely always on the cusp of getting big enough to support ourselves with it.

We tried (and failed) to raise last year, so still entirely bootstrapped. With funding down right now another attempt at a raise doesn't seem like it's in the cards.


I almost forgot I run this project. It makes less than 1€/month average :D.

I built https://banco.surf, which gives you API access to your european bank account's transactions and balances.

The eu-only restriction is a matter of the PSD2 provider I use.

Price: 1€/month per account. Prepaid. No subscriptions.

It's mostly (and openly) a thin wrapper on top of that Account Information Access provider. The selling point is that it abstracts away a bunch of auth and PSD2-specific processes giving you a trivially integrable HTTP API.

I also offer a first-party Make.com integration.

I use myself a bunch, and occasionally some people use it for some scripting, but not much in terms of MRR or real traction.

Still, costs me next to nothing so it's cool.


An online music locker: http://inter.tube/

You can store your music in The Cloud (mp3 and FLAC supported). Includes a barebones web player and is compatible with the Subsonic protocol so you can use native apps with it. It doesn't do any re-encoding or mess with your files at all so audiophiles might like it.

Inspired by Google Play Music shutting down. I haven't had time to keep adding features but it supports almost all of the Subsonic API. It uses DynamoDB, Lambda, Cloudflare Workers, and Backblaze B2 so it's pretty cheap but I only have two customers. I'm considering moving it to Cloudflare's new storage thing which should simplify it a bit.


Bannerbox: https://bannerbox.io

Embed banners and modals onto your site with no code.

I spent the last 7 years as a growth engineer building banners and modals. Each time there was a custom requirement. I've always thought there should be a Wix kind of experience for tiny components that can be embedded anywhere on a site.

Currently I have 0 users. This year I plan on spending more time on marketing and improving the product. It cost me about $50/month to run. Most is for storage (postgres and redis). A large chunk is for a custom email address through Google. I spend about 1-2 hours working on it every day. I'm thinking long term. Slow and steady.


If I can offer some advice, I'd put some info about what you're actually committing to when you sign up. Your site looks lovely, but there's no info as to whether there are paid or free options or what signing up will actually do (in terms of emails or commitment). I almost never sign up to any service unless they do this, and often if they are open about costs or provide a free tier or trial, I'm much more likely to test it out.


I've made yet another magnetometer, but this one its free and no ads. It helped me locate a strong magnet in a hole I had put 5 ft underground. I was then able to excavate to it and install my main water line without digging a huge hole. check it out at: https://www.smartbrosltd.com


I didn’t even know this was a thing that was possible, let alone yet another, and Free!?

Thanks. I’ve been looking for something like this or some sort of sensor setup to do the same.


Thank you!


Sounds like an interesting story that I'm curious about... how did putting a strong magnet in the ground help you install your main water line?


I had the main rupture under my floor which is a concrete slab. so Instead of breaking the concrete I routed a new line from the outside directly to the back of my bathroom wall, where there was a small space behind the shower to access the plumbing. Luckily there was no concrete underneath the bathroom tub so I made a hole with a power washer and a very long extension wand for it, directly vertical. In this hole I put the strong neodymium magnet. Now from the outside I was able to locate exactly where my other hole was with my app. This way I was able to install a new main into my house with no damage to my structure.


Neat! Thanks for sharing!


I'm actively working on two projects currently making $0 (and I don't necessarily mind):

Mastodon Chirper - A browser extension which injects Mastodon posts into your Twitter timeline. Great way to transition to Mastodon without leaving Twitter. https://chirper.picheta.me/

Mousetrack - A price tracker and deal finder for Walt Disney World holidays. I hope to make it the best source of data for how prices for these holidays change (especially during our current high-inflation times). https://mousetrack.co.uk


Not really expecting a revenue, just hacking around.

Almost all grateful dead and Jerry Garcia concerts in telegram https://t.me/gdvault it would be nice if someone can remake all of it because it ended up quite ugly with song listings and overall structure. It's all in bash and code quality is quite bad, but I can throw it on GitHub of somebody interested.

Xscreensaver with imgui https://github.com/yekm/imscreensaver only one for now, made it in a weekend just to proof of the concept. Help wanted


My latest side project is still in figure-out-how-to-get-users mode:

https://feelers.online/

The idea is to give content creators (authors, YouTubers, webcomics, bands, etc.) a way to inform their fans when new content drops. It also gives the fans a lot of control over how the notifications arrive.

I made this to address a problem I experience myself. I operate a website that publishes on an irregular schedule, and it can be hard to let readers/listeners know when we have something new.


I just launched Find Humane, a free website and app for finding humanely raised animal products: https://findhumane.com/

Currently $0 revenue but we have some affiliate links to humanely certified delivery services, so hopefully the ball will start rolling!


I think this has potential for a certain target audience. Not a criticism, but feedback: if I stumbled on this site I'd have no idea what it was about based on the current landing page. Will you be adding an intro/description about what the site is for? :-)


Thanks, great feedback. I'm using the same code for web and mobile apps (Expo/React Native), but mobile users have gone through the app store landing page, so I agree it makes sense to add a landing page for web users. I'm thinking of a small little pop-up on first visit, but let me know if you'd prefer something else.


Small side-side issue, it seems you have a typo, without Javascript I get:

JavaScript is required to be not enabled in your browser.

Reload


Thanks! I'll fix that in the next release.


I've been working on a videogame project for the better part of a year now (a construction and management sim inspired by Factorio, Stardew Valley and similar games, combining concepts and mechanics from all of them), writing my own engine on top of SDL2.

It's not the most original idea and I doubt it will ever actually see the light of day but the main point of this project was to get into C++ (coming from Java) and I think it served its purpose very well.

In reality it didn't cost me anything but I technically "wasted" many thousands of dollars of my time on it...


https://kindmind.com.

It's an online journal with a focus on mental health and wellness I've been building since 2015. I gave up trying to find my version of the perfect online journal and decided to build it myself.

I started accepting donations earlier this month to help offset operating costs, so technically I've made a grand total of $15 income over these last eight years, minus about $8k expenses give-or-take out of my pocket.

Overall, it's brought much joy and purpose to my life. Hard to put a price on that.


During covid I wanted to take a 'digital vacation', so I thought: why not an online chess lesson with grand master Ben Finegold? But arranging a time (across busy schedules and time zones) and price was too much effort for a once-off catch up, so I made a tool that would have let me google him and book (and pay for) a time in under 1 minute (with trivial effort from both parties). Of course, it works for anyone, not limited to chess GMs.

https://www.hangswith.com/


Surprising you don't make money off this. Works well with Humble Bundle style pricing, with a tip or portion given to charity.


https://gatesnaplabs.com

Idea: Make software for the Olympic sport of bicycle motocross.

Execution: Flawless. Built the app in Elm + Ionic Capacitor. It looks great and works perfectly. There's even a Web version at https://gearbag.bike

Marketing: lol

Result: I have spent five digits of money (paid my friends market wages for their help, particularly with UX and design) and made $6 from Google AdMob and have ~100 installs.

Worth it. Doubling down on the next project this year.


https://acos.games

I created a platform and simulator for developers to create multiplayer turn-based browser games using JavaScript. It's been in development for about 2 years and online for 1 year.

The plan is to allow all games to have ranking and competition features automatically built-in.

It has tons of carefully crafted features, but I have failed to gain any interest in the project, so its just sitting there waiting for someone to love it.

I am losing $60/month on the dedicated server the whole infrastructure runs on.


I played one of the games after seeing it on HN a while back, and it’s very polished! But… I don’t have a lot of free time to play games like that :(


Thanks =)

Web gaming seems to be a niche area these days.


https://wishy.gift - A privacy friendly wishlist service, made for my SO after she got 4 thermoses for Christmas a year and only needed 1. Costs ~$30/mo, but is used by my entire extended family, which makes it all worth it :)


So I just started on this a week and a half ago, but thanks to a recent layoff, I'm able to churn through it a little more quickly than I thought I might be able to, and I don't anticipate it ever making any real money, so I think it counts.

The gist is that it's a site for imagining who would be cast into the roles of comic books, anime, books, or old TV series (or film) if they were adapted into modern a modern movie.

It was originally born out of the idea when The Dark Knight aired, and I was pretty confident that Heath Ledger was going to be good, but when I was chatting with a different group of friends than those who had already heard me say that, nobody believed it. So the first pass of it was just a simple form of social proof, but the more I've thought about it over the years, the more it's evolved.

It's pretty useless right now, but at the pace I'm going, I should be able to have a workable MVP in the next few days before I have to start looking for another job.

https://fancasting.com

The frontend is Next/React, and the few 'backend' pieces are also Next API functions (which isn't something I've really delved into before, so kind of fun, ignoring the weird latency effect of functions) - the only thing that currently resembles what I'm used to as a backend is the Planetscale DB, which it speaks to via Prisma.


endoflife.date: https://endoflife.date

Created it because I was frustrated having to lookup information on multiple sites, and having to dig deep and read through terribly written support policies. No Ads, no tracking, all hosted cheaply on Netlify OSS Plan.

Now at 100+ contributors, with 3-5 maintainers on the project. We have a long roadmap for the next year[0]. A contributor wrote a EOL Scanner that is based on a fork of grype[1].

[0]: https://github.com/endoflife-date/endoflife.date/issues/2108

[1]: https://github.com/noqcks/xeol


This is awesome! I would love is Swappa pulled from your api and could show device support. That could be an idea for a little browser extension.


Thanks for that! That looks extremely useful...


great resource. thanks!


https://privtracker.com/ Private BitTorrent tracker for everyone

No plans or even ideas how to commercialize it, so it will stay at $-10/month.

I made it just for fun, but noticed that there are some users, so I keep it running.


https://www.reciped.io

Wikipedia like recipe site. Drag and drop meal planning, and automatically creates grocery lists sorted by grocery aisle. Grocery lists are built for mobile, swipe right to slide that item off the list.


https://golfcourse.wiki

It's a wiki for golf courses. I am a bit embarrassed to love golf, but want to create a platform for smaller courses to be seen along side their private fancy counterparts. I currently lose a dozen or so dollars per month to run it, but that will increase as the site grows. I'm not entirely sure how I'll run it if it ever really takes off. I've considered trying for c3 status, because I don't really need the money, but I'm not sure whether or not that would be the limitations imposed by that would be.

The one thing I want do want to say is that I want courses that are open to the public to be able to use the materials created on the wiki at their location. An entry can be as simple as a blurb with a link to the course website, or as complex as a detailed mapping of the entire course and greens (the different color flags on the homepage indicate different levels of detail).

So, if someone maps a public course, that course can use that person's work on their scorecards instead of hiring and outside graphic designer. It effectively allows public courses to get detailed course guides for free and sell them onsite to raise revenues, but also provides a free alternative for folks online. I want it to be a way that people can casually spend their time to reduce the costs of golf, especially for cash-strapped municipal courses. Golf is too expensive, and this site should be a way to reduce the costs and make the game more accessible in general.


Privacy-First Jobs - a job board solely for privacy-focused companies and orgs: https://privacyfirstjobs.com/

Direct feedback from users is consistently positive but I’m starting to think a job board based around values is not the great idea I thought it was. Nevertheless it’s still something I think should exist (and I might need it myself one day), so as long as the cost to keep it running is low, I’ll keep it running.


Dollero - https://dollero.app/

Dollero is a personal budgeting web app which doesn't store any of your budgeting data in the cloud. Instead your budget data is stored locally in your browser with IndexedDB and is synced peer to peer with your other devices using WebRTC. It's currently is free and makes no money although I would like to eventually charge a small monthly fee for syncing your budget between devices.


I’m planning to create a privacy focused budgeting app as well. My idea is to have the user data backed up to their personal google drive instead.


This ask HN is great.

I'm discovering quite interesting projects.

Here's mine:

I write a newsletter about mental models for entrepreneurs.

Most content on the topic has too much jargon and is boring. So I'm trying to explain these useful ideas with business stories. And in an actionable way.

After some iteration, started getting positive feedback and just crossed 4000 subscribers.

It's free. But I'm planning to start monetizing it with sponsors soon.

https://fronterablog.com/newsletter


I've been running my website + blog + newsletter + map [1] since 2018, and while I made about $900 in revenue in 2021, last year I generated $0.

The website is a compendium of all the coffee shops I've visited in the metro Atlanta area over the last five years + dozens more in the travel section. The monetization angles I have tried include the Membership (reader-supported) model and the Sponsorship (company/brand) model (with a nod to Packy McCormick's Not Boring newsletter for the "Deep Dive" approach, which I am a big fan of). Coffee shops may also post paid ads to barista jobs on the "job board" section of the site.

I wrote more about publishing content online, monetization strategies, and more in a recent blog post, for those curious [2].

I recognize that this forum is more focused on products, but I think some would appreciate the effort in trying to scale a blog/website with incremental products/services available to a dedicated audience.

[1] https://atlantacoffeeshops.com [2] https://www.atlantacoffeeshops.com/blog/a-brief-update-on-th...


RoadCaptain: https://roadcaptain.nl/

It’s an add-on to Zwift that lets you create your own custom routes and not be limited to the fixed ones offered by Zwift.

I’ve been working on this for a little over a year and I’ve had some good reactions from folks using it.

Even so, apart from one person sponsoring me on GitHub with a one-off that’s it money wise. I’ve been toying with the idea of a paid version but no clue if that’s even worthwhile to do.


Really impressive work, love the runner app and looking forward to going through the code.

I had an idea for using a 3 button keybow for use with the Zwift app for navigation/power-up features.


Thank you!


https://hbit.app

I made this app to inspire people to habitually and spontaneously exercise and to be physically active as an integral part of life. You can use the app solo to discover and share new exercises. And you can use it with friends, family and colleagues to challenge each other and to battle it out in combat mode (competitions of who does more repetitions).

Availability: Android and iOS

Price: Currently free

Cost to me: Time and effort to build, adjust and update the app.

Why do it?

Exercise and physical activity have a very positive impact on my life, especially mentally. I think that a lot of people tend to look at exercise as something that primarily benefits their looks though and hence as something they should be doing, without seeing much (if any) joy in it.

Personally, I have no exercise goals, I don't schedule time to exercise, I don't look at exercise as something that I dread or have to do and I eat what I want and as much as I want. For me, the most important benefits of exercise and physical activity are that being physically active makes me feel good and that it clears my thinking. Physical fitness is merely a nice bonus that comes with it.

So the aim of the Hbit project is to sway people's perception from exercise as a dreadful chore to exercise as playful fun.


I review bad, low budget, and obscure movies on youtube: https://www.youtube.com/@calhounsreviews still less than 300 subs but I keep making them because I enjoy it!


Thanks for posting this, I like low-budget and obscure, so you just found yourself a new subscriber!


Thanks!


The Animator: https://theanimator.co.uk/

Originally an experiment when the HTML Canvas element was new and exciting, to see if I could make a website to create flip-book style animations. I have no proof, but I'm pretty confident it was one of the first websites that could do so.

~12 years later, a refactor from PHP to NodeJS and React and LOTS of spare-time sunk into it - it's moderately successful by my standards. Got kids from all over the world creating stuff - some even very impressive. From my logs, I can even see some schools in the USA are using it in some lessons.

It's been a pain sometimes when troublemakers are hell-bent on making, well - trouble! Definitely build your moderation tools from the start folks.

It has a few ads sprinkled over it in a futile attempt to cover my server costs, but probably has a net cost to me of about £20/mo.

Genuinely love that kids and teachers use it - even my daughter is on there. It's been absolutely fascinating and heartwarming to see how some of the kids have developed their art and animation skills over time. Maybe one day it'll be bug-free and "finished".


Do you do any marketing? Do you share/ promote to teachers?


No, never marketed it. Had vague ideas to do so - but thought I needed some more admin functionality first. Things like being able to white label it for a school, upload CSVs of student accounts, those sorts of things.

Those who do already use it must have just discovered it by search or word of mouth.


This is really nice!


Thank you kind guy of physics :)


502 bad gateway


Thanks - fixed. My server died a horrible death when another project spun out of control.


iOS app Blind Compass https://github.com/mltony/blind-compass

I am blind and I developed this auditory compass for blind people that communicates your heading as two tones - musical interval between them encodes your heading. It helps white cane users not to get confused in space or walk straight across large open space by locking heading. It also makes me look like a lunatic, because I put iPhone into phone holder that I sawn to my hat to provide most accurate heading information.

The app is free, but I have to pay for Apple Developer subscription to keep the app in the app store.


This is brilliant! It reminds me of the North Paw anklet, which I think dates from back when phones didn't include magnetometers.

If I keep my phone in a hip holster but get the audio over a Bluetooth earbud, is that likely to be useful? Do you wear it on your hat so you can swivel your neck and "probe" the compass response, or because you get better results up there in some other way?


I do use it with bluetooth headphones - bone conductance headphones, so that I can also hear the street. I tried to put my phone in the pocket, but then heading fluctuates with every step. I assume this might be enough for someone, but I prefer to hear accurate heading, wich allows me to walk straight comfortably.


> I tried to put my phone in the pocket, but then heading fluctuates with every step.

As you're the developer (and a blind user eating your own dog food) I might suggest (for those that want to put their phone in their pocket) looking at using a running filter to smooth the headings and remove the swing of every step.

Savitzky–Golay filters are particularly good for this and (pages of complicated math aside) are really as simple to implement as a straight running average (as you multiply a string of heading values with normalised weights and sum to get the "better heading" .. add a new heading to front of string, drop off the oldest heading from the back, repeat).


It gets into a lot more code, but integrating the accelerometer readings to figure out where in the step you are, and correct the magnetometer readings, could work. It would have to relearn any time the phone shifted in your pocket, but that could become a continuous process while walking.

Probably easier to just put the phone in a hat, though.


https://javascript.onl/

Wondered a while ago if I could make a static website where you could solve interview-style JavaScript problems in the browser. It uses web workers and local storage. There are Amazon affiliate links on the website for some books, but the account is suspended. It's hosted on GCP and I lose a few cents a month to keep it up.


https://github.com/rbanffy/3270font

Being distributed with Debian and downstreams, 11 years old, with 1.5K stars and 60+ forks is, by far, my most popular open source thing. My biggest shame is that it's not software, but a font that mimics the look of IBM's 3278-2 terminals.

And, of course, it's the font I use for terminals on all my machines.


Well, I started my project, a file manager in Java named Ant Commander, in 2003. It was a shareware. It never sold.

Still didn't give up the project, as I use it every day. So last year I decided for a big refactoring (Ant Commander Pro) and to specialize it for developers.

The beta is for free but then I'll be charging again.

https://www.antcommander.com/


https://heylaing.com - just here to help you practice your language. I got frustrated not being able to properly practice Spanish, especially for listening and speaking and did not have time to find a practice partner so started to create something that would allow me to practice my language skills in a more realistic setting....heyLaing was born. There's a whole lot more to the story but that's the tl;dr.

It was great for me to learn how to code and design. I've always been able to code a little bit but this was my first real product. I realised I still suck at both coding and design but it's helped me so much, and helped me learn Spanish far better. It costs me about $5 a month to run this on a droplet from Digital Ocean.

It's been great for my mental health and also concentration, i love putting my Product Manager hat on and solving the 'problem' and then figuring out how I am going to code it.

I also now get about 1-3 new sign ups a day since 'launching' with a few posts on reddit a few months ago.


https://game-watch.agreon.de (I know, my naming is great) is a service to get updates for games that you are interested in.

I'd often watch game release previews like the E3 and put the games that interested me in some kind of list. Now I would have to check manually for news about a release date or in which stores they would be published. GameWatch takes off this work from me and maybe also from you :).

I know it was most probably done before in some similar way, but I didn't even search for alternatives until now. It would have been a good idea if I wanted to create a real market competitor, but that was not my motivation. I wanted to craft something that was my own, and not a copy of some product. I didn't want to spoil my creativity.

I guess the most asked question will be: Why don't you crawl all the games beforehand and let the user search in your database. After all, it would improve the usability as users would not have to wait for the crawl to happen on demand. Also, you could show useful information like price history etc. per store.

Well, besides the limited resources I wanted to invest, the project was born with a different idea than price monitoring in mind. Rather, the main idea was for me - as a user of many game devices - to get updated as soon as a game is added to a specific store (Maybe some games would be nicer to play on the Switch?).

A preliminary crawl would not really have helped in this case. Besides, the on demand crawl results are cached. So if a popular game is searched for often, the overhead won't really be noticeable.

Costs:

- ~5€ DataDog Logging

- ~10€ VPC (but that is also used for other things)


https://scrabble-solver.org/

It's open-source too: https://github.com/kamilmielnik/scrabble-solver

I never intended it to make any money though. What brings me a lot of joy is that some people showed genuine interest in this project.


Game Boy Essentials, my attempt to catalogue the appeal of the Game Boy. I write articles online, and then turn them into a book every twelve articles.

I moved from hand-coded HTML to Jekyll, and published my first book using Pages from Apple to make the PDF, but now use XeTeX and a custom HTML conversion to make my books with a single button press.

I used to use Kindle Direct Publishing (née createspace) but have very wisely moved on to Lulu. Amazon had banned me for using content readily-available online. I appealed and got my account back but they still haven't resolved the problem with my books. I totally blame the recent staff cuts at the company.

Lulu is slightly more expensive for my customers but the books are colour and I don't feel like I'm using the forgotten service of a company who doesn't care.

The website is hosted on AWS using S3 and Cloudfront, my registrar is Amazon and I'm absolutely looking for an alternative if anyone has any.

I'm at https://gameboyessentials.com


I made a real estate thing that basically scraped a bunch of data and then built a NLP query interface on top to query real estate data in natural language.

Couldn't find a customer so it makes $0 haha. Here's an example of the system working, minus a pretty UI: https://imgur.com/a/ITDKtPC


Does ruby have an NLP library or are you rolling your own?


Built a separate service that used spacy


I shouldn't be surprised but the amount of posters heavily pushing for ads or gambling (loot boxes) is disgusting and horrifying.

Not everything needs to make money, especially for community projects.


Recently decided to launch MessageDuck: https://www.messageduck.com after working on a few side projects but never actually launching for many years. It is similar to Mailcharts and ReallyGoodEmail, but for SMS which Mailcharts has as well but the price is out of our range.

Basically it is a library of thousands of SMS messages to help marketers get the latest SMS data and launch their campaign in minutes instead of days. Currently earning $0 and incurring some cost of about less than $100 a month but overall it meets our own need. It was an internal tool we used but we decided to launch it to the open web and see if there was any demand for it. Currently it has all the features of a MVP and already works great for us but we are adding some new features every month as well.


This is actually incredible useful for what I work with, very cool to get a pulse on brand strategies. How did you get the data in?


Thanks for the comment! We started with subscribing to some brands manually with our own number to see if the idea was viable for about a month before trying to do it at scale by looking for which brands offered SMS and using something like a Twilio virtual phone number to get the message they send to us via API to put in the database. We currently spend a few hours every month to do that and to add more features.


I made a couple of clocks:

https://sunclock.net - 24 hour analogue clock showing sunrise, sunset, and twilight times, and position and phase of the moon.

https://bigclock.app - big clock, small page-weight.


I have a wildly unprofitable side hustle as a cattle rancher. Whatever, it’s fun.


How did you get started on this side hustle?


More money than sense.


I built a tool for predicting the outcome of matchups in Yahoo Fantasy Hockey (head-to-head category based leagues). I find it helpful for determining what categories to focus on when picking up streamers/free agents. https://fantasyhockey.fly.dev/

Also, I've seen a few budgeting apps on here. I didn't build Budget with Buckets[1], but I do think it's a great YNAB alternative _except_ that there is no mobile app. So I built a web app that can be used on mobile. https://buckets.goatcounter.com/

[1]https://www.budgetwithbuckets.com/


https://nodablock.com - I create you an Internal Dashboard for your Web3 project with 1 click - I give you Analytics + automatic smartcontract vulnerability scanning + a visualization of transfers between address. A good usecase now is for the Porshe NFT that has some suspicion of wash trading - With my token visualiser [1] you can clearly see the top tokens exchanged between the same wallets.

Not quite ready for a release, but I made it public last week - without talking much about it - hoping people navigating the visualizers and dashboards will reach me out. But it's still not making money.

[1] https://nodablock.com/nft/porche-911


https://wrolpi.org/ Been having a great time on my side-project WROLPi. Its preparedness-oriented software which allows you to create an offline library. Videos, web archives, maps, epub/pdf, etc. Really easy search, low power usage if you run on in a Raspberry Pi. Just put out the first Raspberry Pi image, which makes installation super simple. Hoping to get a Debian image soon.

Currently "videos" is pretty well flushed out. Still some work to do with web archives. Maps has been a huge headache simply because maps are so large. Got PDFs and EPUBs searchable recently.

An abbreviated list of the technologies I've used to built it: Python, ReactJS, Open Street Map, yt-dlp (videos), SingleFile (web archives).


Oh this is super interesting! I've been playing with Internetinabox, Kiwix, yt-dlp, httrack'd websites, mirrors of github orgs... and I have all this data but no frontend for it. Searchability is huge, I will definitely be playing with this.

IIAB, notably, has an offline maps function in recent versions. I haven't looked at how it works.

Ultimately I'd like to put _all_ that content behind the same interface as my local Othernet receiver node, some sort of Piratebox file-upload site, a local-only BBS sort of message-board, and whatever else might be useful if I found myself offline for a long time.

Oh btw, this may be of interest since you're likely to have a pi sitting there, maybe you'd like to bring up some other pis:

https://blog.thelifeofkenneth.com/2018/01/off-grid-raspbian-...

(I've also recognized that, since I'm likely to have a bucket of Arduinos and stuff around but I'm hopeless without example code, I should have that somehow. So I have the kiwix dumps of raspberrypi.stackexchange and arduino.stackexchange, but I also mirrorred adafruit's and sparkfun's entire github orgs. I need to find a way to httrack waveshare's and seeedstudio's wikis, but they're very crawl-resistant....)


Thanks for the reply. Your comment about having it all behind one interface really resonates with my goals with WROLPi.

I skimmed the link you provided. My goal is to do something similar, but use the Debian Blu-ray ISOs. Debian provides ISOs that contain their entire repo. They fit nicely on a 128GB thumb drive.


My pandemic project is VanWalks. It's a walking tour app of Vancouver. There are currently 5 routes around the downtown area. Working on a freemium model, Chinatown and Coal Harbour are free, the rest are in app purchases.

Available in both app stores and the site is vanwalks.ca

I'm currently working on making a web version of the app because my sales model is in a very grey area as to what Apple allows in their store. I want to be prepared in case Apple takes my app down.

I'm working with the BC Entertainment Hall of Fame to provide a free walking tour of the Star Walk on Granville Street. I'm also working with the Vancouver Police Museum to digitize the walking tours that they offer and have them in the app as part of your admission to the museum. Those will both be launched this spring.


Here's something I'm just starting on:

Find your dream RV. http://rvenvy.com

With more people than ever working remotely, many are interested in ending their lease and exploring America – even moreso now that Starlink is widely available.

At this point, it's a directory site, but I aim for this to be the Wikipedia of RVs.

But if you don't know RVs, it can be daunting to figure out what you need. That's why I also created a Bubble app (as a prototype) that offers a wizard to help you find exactly what you want. It asks a series of questions in a TurboTax-style wizard:

https://concierge.rvenvy.com

Right now results are shared manually, but eventually this will be automated.


Hahaha... I like this one. Here's how I lost money for 25 years building failed businesses.

https://joeldare.com/how-to-lose-money-with-25-years-of-fail...


A small team and I made https://woogles.io - we were inspired by lichess to make a site to play crossword board games during the pandemic (like Scrabble, Words with Friends, etc).

We did raise money on Kickstarter - 25K but are purely donations-driven and open source (AGPL3) Most months we just get enough to cover the cost of running the servers. We have around 6000 monthly active users, have hosted several big worldwide championships, have puzzles, and just earlier today released a board editor / broadcast mode for annotating real life games in real time. We also have a top notch bot AI and WASM-based analyzer.

Our stack is Go, Typescript + React, with NATS/PGSQL on the backend.


Who’s Hosting SNL : https://whoshostingsnl.com

Very simple solution cause I was angry I couldn’t just google the question and get the answer without a few clicks and scrolling.

Costs under $10 a month hosted with cloudfront and S3


Partisan Playground:

- https://partisanplayground.substack.com/

- https://twitter.com/PartisanPlayG

This side project attempts to quantify the news cycle and show what each "side" of the media is covering. I've had this for a few years but never attempted to monetize it. It runs every day and is nearly 100% automated.

My goal is to add text to the newsletter that describes the data using GPT-3. Then I will use the newsletter as a POC and pitch to others: I can create fully automated reports that take your data, analyze it, chart it, and describe the analysis.

Any thoughts about this idea?


Thank you for sharing. I really dig the PartisanPlayground site/idea. Very well executed. As for the idea to extend that as a service to analyze other types of data, it sounds fascinating. When you say "others", do you have an idea who your target market would be? (e.g. government? enterprise? SMBs)?


Thanks! I was thinking internal reporting at enterprises would be the first place to start. I could automate reports that analysts manually generate. This would cover 90% of the report building process for them, with the remaining 10% being editing the AI report output.


This is cool! How do you categorize “right” and “left”?


Thanks! I use the media bias ratings from AllSides: https://www.allsides.com/media-bias/ratings


https://superstrong.app

Heavily inspired by other weightlifting trackers such as Strong and Hevy and can import your history from those apps.

Includes a heatmap (similar to the github commit one) that shows your weekly history. https://pbs.twimg.com/profile_banners/2888157513/1674607291/...

Its a mobile first PWA so you can install and get a very native feel, but also use on your desktop.

Going to be adding sync with google sheets soon as well to allow for complex weekly programming (e.g. adjust weights based on last logged workout for a given template)


I created https://dropory.com/ - an app that predict the day with the best weather for any location. Good for finding a good event or wedding date.

Definitely been costing me more than any earnings! :)


Golden Squirrel: goldensquirrel.io

Premise: Get all the upfront information you need to know as a software engineer before applying to a job. Accompanying podcast called "Chasing Squirrels".

Price: $0 (implementing stripe next to charge employers for job posts)

Cost to me: $500/mo in SaaS fees + podcast related fees

Why do it? I became frustrated with how hard it is to find information about the engineer you'll actually be working for at the job, which is one of the biggest if not the biggest factor in looking at new roles. I wanted to de-risk the hiring process for devs by providing as much info upfront about the compensation, role, what they'd be working on, etc so I started with the podcast and just build the job board recently.


I’ve made roughly -$400 so far from my jazz sticker business, https://www.jazzstickers.com. Not trying to make money, only to roughly break even and make more of my ideas happen.


Thanks for introducing us to your products. Glad to have found you (and I just ordered a couple!)


Thanks!


Todidlist: https://todidlist.com

I built a web version of my original plaintext did.txt file. Plaintext is great for computers but I wanted a way to do a "did" ritual on iOS devices.

There is 1 user, me. I feel like all the benefits comes from using it like a journal so I never actually read the dids or built any features to query them well.

Original did file post: https://thepatricktran.com/2018/07/11/did-txt-file/ ** I lost the theptrk.com domain because I forgot to update my credit card.


CodeApprove: https://codeapprove.com

Basically CodeApprove is a code review UI for power users to layer on top of GitHub. I find that it really resonates with people who have worked at Google/Facebook/etc before and find Github's code review tools really lacking. You get conversation resolution tracking, auto-assignment of reviewers between 'turns', a personalized inbox, and a dense/fast UI with keyboard shortcuts for almost everything.

(Note: I do have some users, but I just got out of alpha mode haven't yet charged any of them. I will get my first $ at the end of this month)


After reading on Hacker News about Universal Paperclips and seeing someone post that their whole team wasted a day playing it, I thought I would try to create an idle game that was devops themed, collaborative, and time-limited.

Like other idle games, you basically try to make the big number get really, really big. But, unlike other idle games that I have found, mine mixes in silly devrel trivia questions. Set aside exactly 20 minutes to get your team working together to accumulate an absurdly huge number of successful unit test runs in a truly test-centric world:

https://greens-io.appspot.com


Why does loading ("Checking...") on answer submit?


I wanted players to think about choosing the right option rather than just submitting every choice like trial-and-error. If you get it wrong, you can try again, it just burns a little of your time.


Neptunely: https://neptunely.com

I've been building a procedural music generation engine for the last 2 years. It's been a passion project. There are a handful of videos on youtube that showcase it. It can generate pretty good songs and transitions based on established rules. I'm hoping to make it more generally accessible soon, but so far I've just been using it to help me make my music: https://open.spotify.com/artist/3Xtq9IlfA0l3dNPe3lhGAY


Fascinating, thanks for sharing! (fellow musician/composer)


Introducing macOCR - a command line tool that revolutionizes how you capture text on your screen!

With just one command, you can instantly convert any text on your screen into text on your clipboard, making it easy to use in any app or program. Plus, with support for popular launcher apps like Alfred, LaunchBar, and Hammerspoon, it's never been easier to access the power of macOCR.

And if you're feeling really advanced, you can even use it to feed data into an OpenAI large language model for advanced text processing.

Upgrade your text capture game with macOCR today!

Price: $0

MRR: $0

Copy reworked by: GPT

Prompt: “Rewrite for hacker news:”

URL: https://github.com/schappim/macOCR


the anti captcha!


Citybikes: https://citybik.es

A bike sharing data aggregator. Started as an Android app for my local city, then an app for any city and then just decided to offer an API for free and let other people create apps, visualizations or research based on it.

Been running it for over 10 years. Major transport apps use it for bike sharing data (like moovit or citymapper) with zero contributions to our project. I am proud that there is at least one FOSS app for each major platform out there using the API, which kind of was my idea when offering the free API (and not big players leeching from it).


Very cool. I just checked your site after some time and happily saw that my city is now supported. Upon checking in the API, it's using the unofficial GBFS feed that a couple friends and I are hosting (which we're also earning 0€ from).

We built our own GBFS GraphQL abstraction called gbfsQL [1] a couple years ago that makes working with GBFS less difficult.

[1]: https://github.com/mapintelligenceagency/gbfsQL


Thanks for replying and for providing feeds much on the same philosophy as citybikes. I guess the feed you mention is for Aachen [1]? Sometimes I take a very hands-off approach on the library contributions, so I do not know about specifics. At the moment our gbfs feeds come with a 'gbfs_href' field mentioning the source. Is there any way on which I can give more credit to the work you are doing? It would suck for our project to perpetuate the same kind of damage we receive from other projects, so this is important to me.

Will send you an email, happy to chat.

[1]: https://github.com/eskerda/pybikes/blob/86c8cca04b9e747fda1e...


Honestly, I am just happy that someone is using the GBFS feed. We built it for and are using it on Openvelo [0] which I don't think many people use. The purpose was never to somehow be rewarded, but to make working with this kind of data in our city easier.

[0] https://openvelo.org/


https://historicalchristian.faith/

An open source database that pulls up all historical Christian commentary on a verse in the Bible - e.g. see how the early church fathers interpreted a verse, it's often illuminating.

Was inspired by CS Lewis' comments about the "Old Books": "Every age has its own outlook. It is specially good at seeing certain truths and specially liable to make certain mistakes. We all, therefore, need the books that will correct the characteristic mistakes of our own period. And that means the old books."


This is awesome! I'm certainly going to be taking a look. I've been reading from C.S. Lewis's letters recently and found a lot of value, so it is especially nice to read this!


Not quite ready for prime time, but I've spent the last couple of weeks building a fast, free, parametric part library for makers to use for widget-type parts rather than complex models. I found the current set of part libraries to be to slow and/or cumbersome for my tastes.

It's 100% static and hosted on GitHub pages. It uses WASM versions of OpenSCAD and SQLite for dynamic content with all processing being done in the browser. Parts are added as GitHub issues, and can be added by anyone with a GitHub login

https://parapart.com

Next step: Content!

Note: Currently not mobile-friendly.


Checkout https://make.craftyamigo.com/, might be something on your roadmap. https://twitter.com/navidsafa/status/1604294611278643200


Marqus: https://github.com/EddieAbbondanzio/marqus

It's yet another markdown based note taking app. I wanted something that gave as much screen real estate to the note's content vs navigation so it'd be easy to use on small screens, and I also wanted to save my notes in plain files vs a proprietary format.

I don't plan on charging any money for the app itself so it'll never make me any money but I do plan on offering an optional note syncing service for multi-device support that'll be a few bucks a month.