Hacker Newsnew | past | comments | ask | show | jobs | submit | felarof's commentslogin

gpt-oss 20B works well. You'll want at least 12k context length for agent mode.

Thanks!

> whole Browser and not a Chrome Extension argument

Both of us are definitely biased to think our own approach is better :)

But without owning the binary, we couldn't shipped today's feature -- Agent with access to your filesystem and being able to run shell commands like Claude Cowork.

> your interface is still literally a chrome extension side panel

Yep, our interface is a chrome extension to make iterating on the UX faster. But it uses a ton of C++ APIs that we expose under `chrome.browseros.*`

> Your workflow pipeline is really cool! Any blog post/summary on how you set it up?

Thanks! We'll look into publishing a blog soon!


> But without owning the binary, we couldn't shipped today's feature -- Agent with access to your filesystem and being able to run shell commands like Claude Cowork

Chrome Extension can also access local files and can also execute LLM generated code in sandboxes


We are still in early versions of the feature! Haven't released on our repo yet.

What use case did you have? Happy to show a demo of current version we have (you can hit me up on discord or slack -- links available on our repo)


Thanks!

> how is it reliably enforced?

At the chromium level, you have access to every single DOM element and coordinate space around it. So, when a click happens either user or agent, we have a neat way of enforcing required action (either allow it or nullify the click).

We are still at early version. And mostly targeting enterprise sites (like SAP) which don't change that often.

What use case did you have in mind?


Ohh, interesting, technically this should already be possible. Because we already package gemini-cli into the sidecar (bun) binary. We just have to create a good UX.

What angle are you looking at this from? Is it for convenience? Or do you not like terminal UI and need a web-friendly UI for these agents?


Thanks for initial feature request! We do read every single request :)

Yes, we expose BrowserOS as an MCP server -- that you can use from claude code, cursor, opencode, etc -- https://docs.browseros.com/features/use-with-claude-code

MCP server works out of box (unlike Chrome DevTools MCP which requires tricky setup).


Good question. We think the browser is becoming the new OS. It doesn’t really matter anymore if you’re on Windows, macOS, or Linux—the browser is where most work already happens.

We see a future where it’s the main gateway to everything, and where agents live and work alongside you inside the browser. That’s why we call it BrowserOS. :)


Is this really true? Mobile device users are all mostly forced to use apps rather than the browser for most stuff, and people on desktop PCs/laptops are probably either using them for gaming (all desktop apps), or work where a lot of stuff is desktop apps.

Sure regular consumer stuff like social media is webapps (if they're not mobile only), and if you're interacting with like salesforce or a customer support tracker or an issue tracker or something you're likely using a webapp, but the move to mobile devices for most consumer stuff means that people still using PCs are largely power users.


> if you're interacting with like salesforce or a customer support tracker or an issue tracker or something you're likely using a webapp

Precisely. I think most knowledge work (especially at business) still happens browser. That is the workflow we want to target!


You have a great business sense!

There is an open source alternative -- browserOS.com


This is exactly our vision as well!

But we want to enable you to run these automations using local models, which would be secure and privacy-first

https://git.new/BrowserOS


You should try us :) open-source and privacy-first alternative to Atlas -- https://github.com/browseros-ai/BrowserOS


Seems like it's based on Chromium? If so, that's a no-go for me. We need more web diversity and support smaller browser engines, we don't need yet another Chromium/Blink based browser.


I agree with this sentiment, but besides Webkit/Chromium and Firefox's Gecko, there's not really any options. Ladybird is a new implementation gaining fast though don't think it's ready to replace everyday workflows yet. And Ladybird has been a huge undertaking of course.

Building a new browser engine is 99% of the work and slapping LLM features on it is the other 1% of it.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: