Hacker News Reader

Comment by ttmacer | Hacker News Reader

It's so great to see now that the folks behind Pi also try to pivot away from the idea that Pi is more than a "coding" agent. Its minimalism, and tool call primitives really lends itself to be a general purpose agent for your OS that you gradually extend on demand for your specific use case.

Since January I use Pi professionally as well as personally and I can only recommend to start small and grow your harness over time. For example, for an agent in production it was so helpful for me to use Pi in interactive mode via tmux to get a feel of the agentic flow, tool calls and reasoning traces for a certain use case while only the stylized responses are rendered in Telegram via an extension to the user. As a Developer, I have full technical observability and control while providing and incrementally improving a service to a user at the same time.

Excited how Pi Durable will fit in and can support more. Congrats and thank you!

View on HN

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?

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.

Codex has a profile feature

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.

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.

Hey thanks for posting this. I use pi professionally too. I am curious how you used agentic workflows with pi before. The simplest(since the early days) was letting it use Tmux for spawning other sessions and controlling it.

The second case, more recent, is one where I use actively now is linking pi sessions to some artifact like a code change(PR or diff) or a collection of document and then continuing the session in that context.

What was your main power case with it.

to correct, I meant "pivoting towards the idea that Pi is "more" than a coding agent"

You have made me excited to try it. Thanks for the tips.

No problem, glad to ignite some spark! Just to clarify, what I mentioned is also effectively possible with other harnesses. Pi's minimalism just made it more ergonomic to focus on the right things and encouraged me to question and thus learn.

Reply on news.ycombinator.com