41–50 of 307 posts
Pi’s minimalism reveals a simple truth: the LLM is the core of any agent harness. Consequently, much of current harness tuning will become redundant(or even a hindrance) with next-gen models.
Earlier quoted context omitted.
Out of curiosity, do you use the pi-xmpp[1] extension or do you have your own? [1]: https://pi.dev/packages/pi-xmpp
Initially I was using that extension but I ran into its limitations pretty quickly. Sometimes the agent wouldn't reply over XMPP, it didn't have any support for typing indicators or status messages, and it had no way to support inter-agent communication, the agent could only ever speak to the configured owner account. I also had no way of running system commands like /new over XMPP. The headless pi + xmpp wrapper end…
Pi’s minimalism reveals a simple truth: the LLM is the core of any agent harness. Consequently, much of current harness tuning will become redundant(or even a hindrance) with next-gen models.
I always thought that the frontier coding models were specifically trained to perform well in the harness from their providers. I imagine this will always be the case to some extent.
Earlier quoted context omitted.
I have the same opinion as your first paragraph, but I don't want to spend weeks or months vibe-coding basic features which come built into almost every other agent. Yeah maybe Claude/OpenCode/KiloCode/Hermes/whatever are not as minimal as Pi but they also work right now.
You don't actually need those features. Initially I began using Pi thinking I would customize the hell out of it. I've installed one extension for guardrails and that's about it. I've been able to do everything I did before just with vanilla pi.
Earlier quoted context omitted.
I find omp funny because it's the opposite of why Iike Pi.
It’s more like a curated config. Like using Astro or Lunar instead of starting with a plain Neovim and crafting your own configuration.
Earlier quoted context omitted.
You don't actually need those features. Initially I began using Pi thinking I would customize the hell out of it. I've installed one extension for guardrails and that's about it. I've been able to do everything I did before just with vanilla pi.
What extension do you use ? With all the supply chain attacks I am warry of adding extensions, so I wonder if there's like a go-to one that everyone uses
Aside from the minimal system prompt, how does it handle context better than other agents? It still has to send the system prompt (which includes AGENTS.md and skill definitions) along with the full conversation every request, no?
A lot of harnesses compress the context when it becomes massive, Pi doesn't do that out of the box (EDIT: that's wrong, as pointed out below). It can be both good and bad. Also since it doesn't have a lot of tools out of the box, the context is not polluted with external tool call descriptions that the agent has to be aware of. Basically, it doesn't handle the context "better", it barely does anything special to it,…
Having tried all the coding harnesses, I find that using Pi is exactly like using Emacs. For anything you want to build you can ask your agent and it will build it. There's tons of existing code to help you configure it. At the same time half the code is buggy, UI elements will try to overlap one another, and you'll periodically get crashes. If you're willing to put in the work to master the learning curve and push t…
I don't really get this philosophy, at least with coding harnesses. I don't want to spend 2 hours prompting, configuring and fixing features that I need which are standard in every other harness. I don't really want to be wasting my tokens to make an application function like every other harness. I don't really want to have to repeat the cycle on every machine I want to work with. Every VM, every server, every laptop…
For instance the XMPP integration someone mentioned allowing agents to talk to each other and to you remotely; or custom extensions to enable workers to be tmux aware; or adding whatever memory system you’d like; and so on
Aside from the minimal system prompt, how does it handle context better than other agents? It still has to send the system prompt (which includes AGENTS.md and skill definitions) along with the full conversation every request, no?