Especially with the extensibility of Pi, I‘m wondering whether there is a way to configure different profiles for different kinds of tasks. Such a profile would include tools, system prompt, maybe selected models and their settings.
Is there a straightforward way to do that with Pi?
AFAIK Pi out of the box as other harnesses handles this use case via dot directories on your filesystem. So a .pi directory in your working directory Pi gets started in is the place where you would implement such a profile.
Note that there is also a global .pi in the home directory, which takes precedence over session-local .pi directories.
In the past I used this abstraction conveniently to setup different agents for different purposes. I kinda like having this abstraction on my filesystem to inspect instead of it being hidden away in a opaque harness or, even worse, the weights of the model.
EDIT: then a Pi Extension that swaps .pi directories out, maybe via git worktrees, is just the low-hanging fruit to establish your profiles pattern I think.
Symlink the .pi directory to the profile you want, swapping changes the target of the link inste of modifying files. This is how I implement dark/light mode autoswitches on some of the cli tools I use.
Was also wondering this the other day. Every harness I’ve looked into seems to be monolithic. I would really prefer specialized profiles/configurations instead of loading up every skill and MCP server imaginable into a big stateful works-on-my-machine mess.
I just want to run `pi --profile=./gamedev.toml “build a side scroller where you’re a turtle”` and have it do the thing.
I do this - one profile for work and one for personal. It’s as easy as asking Pi to build it for you. When I run Pi in specific directories it knows which profile to run, using a separate subscription and toolset.
