▲ 608 points
back
306 comments
To me, the most interesting thing about Pi and the "claw" phenomenon is what it means for open source. It's becoming passé to ask for feature requests and even to submit PRs to open source repos. Instead of extensions you install, you download a skill file that tells a coding agent how to add a feature. The software stops being an artifact and starts being a living tool that isn't the same as anyone else's copy. I'm curious to see what tooling will emerge for collaborating with this new paradigm.
I see this happening, too.
We know that a lack of control over their environment makes animals, including humans, depressed.
The software we use has so much of this lack of control. It's their way, their branding, their ads, their app. You're the guest on your own device.
It's no wonder everyone hates technology.
A world with software that is malleable, personal, and cheap - this could do a lot of good. Real ownership.
The nerds could always make a home with their linux desktop. Now everyone can. It'll change the equation.
I'm quite optimistic for this future.
I've been thinking about this lately too. I think we're going to see the rise of Extremely Personal Software, software that barely makes any sense outside of someone's personal context. I think there is going to be _so_ much software written for an audience of 1-10 people in the next year. I've had Claude create so much tooling for me and a small number of others in the last few months. A DnD schedule app; a spoiler-free formula e news checker; a single-use voting site for a climbing co-op; tools to access other tools that I don't like using by hand; just absolutely tons of stuff that would never have made any sense to spend time on before. It's a new world. https://redfloatplane.lol/blog/14-releasing-software-now/
> a living tool that isn't the same as anyone else's copy
Yes, which is why this model of development is basically dead-in-the-water in terms of institutional adoption. No large firm or government is going to allow that.
> It's becoming passé to ask for feature requests and even to submit PRs to open source repos.
Yet, the first impact on FOSS seems to be quite the opposite: maintainers complaining about PRs and vulnerability disclosures that turn out to be AI hallucinations, wasting their time. It seems to be so bad that now GitHub is offering the possibility of turning off pull requests for repositories. What you present here is an optimistic view, and I would be happy for it to be correct, but what we've seen so far unfortunately seems to point in a different direction.
Why would this new paradigm create interesting tooling? From your description I expect wrose not better tools.
Funny, I just released my dev setup as “Open prompt”
> Instead of extensions you install, you download a skill file that tells a coding agent how to add a feature. The software stops being an artifact and starts being a living tool that isn't the same as anyone else's copy. I'm curious to see what tooling will emerge for collaborating with this new paradigm.
I build my own inspired by Beads, not quite as you're describing, but I store todo's in a SQLite database (beads used SQLite AND git hooks, I didn't want to be married to git), and I let them sync to and from GitHub Issues, so in theory I can fork a GitHub repo, and have my tool pull down issues from the original repo (havent tried it when its a fork, so that's a new task for the task pile).
https://github.com/Giancarlos/guardrails/issues
You can see me dogfeeding my tool to my tools codebase and having my issues on the github for anyone to see, you can see the closed ones. I do think we will see an increase in local dev tooling that is tried and tested by its own creators, which will yield better purpose driven tooling that is generic enough to be useful to others.
I used to use Beads for all my Claude Code projects, now I just use GuardRails because it has safety nets and works without git which is what I wanted.
I could have forked Beads, but the other thing is Beads is a behemoth of code, it was much easier to start from nothing but a very detailed spec and Claude Code ;)
I actually look at this another way. I think we’re going to see a lot more open source. Before you had to get your pr merged into main. Now people will just ask ai to build the tool they need and then open source it.
Maintainers won’t have to deal with an endless stream of PRs. Now people will just clone your library the second it has traction and make it perfect for their specific use case.
Cherry pick the best features and build something perfect for them. They’ll be able to do things your product can’t, and individual users will probably find a better fit in these spinoffs than in the original app.
Patrick Collison said this yesterday on TBPN, "Software is becoming like pizza […] It should be cooked right then and there at the moment of use"
My current fave harness. I've been using it to great effect, since it is self-extensible, and added support for it to https://github.com/rcarmo/vibes because it is so much faster than ACP.
I haven’t met a single person who has tried pi for a few days and not made it their daily driver. Once you taste the freedom of being able to set up your tool exactly how you like, there’s really no going back.
and you can build cool stuff on top of it too!
I've been using pi via the pi-coding-agent Emacs package, which uses its RPC mode to populate a pair of Markdown buffers (one for input, one for chat), which I find much nicer than the awful TUIs used by harnesses like gemini-cli (Emacs works perfectly well as a TUI too!).
The extensibility is really nice. It was easy to get it using my preferred issue tracker; and I've recently overridden the built-in `read` and `write` commands to use Emacs buffers instead. I'd like to override `edit` next, but haven't figured out an approach that would play to the strengths of LLMs (i.e. not matching exact text) and Emacs (maybe using tree-sitter queries for matches?). I also gave it a general-purpose `emacs_eval`, which it has used to browse documentation with EWW.
I began with pi, and have been using oh-my-pi the last two weeks.
https://github.com/can1357/oh-my-pi
More of a batteries included version of pi.
I happen to be somewhat familiar with OpenCode and am considering using it as a personal AI workspace (some chat & agentic behavior,
not worrying about initiative behavior just yet, I’d try to DIY memory with local files and access to my notes) because it seems to have a decent ecosystem.
Pi appears to have a smaller, less “pre-made” ecosystem, but with more flexibility, enthusiasm and extensibility.
Is this correct? Should I look towards Pi over OpenCode? What are the UI options?
Preconfigured PI: https://github.com/can1357/oh-my-pi
Hugging Face now provides instructions for using local models in Pi:
Pi has made all the right design choices. Shout out to Mario (and Armin the OG stan) — great taste shows itself.
I've been using Pi day to day recently for simple, smaller tasks. It's a great harness for use with smaller parameter size models given the system prompt is quite a bit shorter vs Claude or Codex (and it uses a nice small set of tools by default).
I spent 3 months adopting Codex and Claude Code SDKs only to realize they're just vendor lock-in and brittle. They're intended to be used as CLI so it's not programmable enough as a library. After digging into OpenClaw codebase, I can safely say that the most of its success comes from the underlying harness, pi agent.
pi plugins support adding hooks at every stage, from tool calls to compaction and let you customize the TUI UI as well. I use it for my multi-tenant Openclaw alternative https://github.com/lobu-ai/lobu
If you're building an agent, please don't use proprietary SDKs from model providers. Just stick to ai-sdk or pi agent.
I still don't get why would you want to use a terminal app to code when you can do all of this through IDE extension which does the same except it is better integrated.
You can open a grid of windows inside vscode too and it comes back up exactly as it was on reload.
Has anyone used an open coding agent in headless mode? I have a system cobbled together with exceptions going to a centralized system where I can then have each one pulled out and `claude -p`'d but I'd rather just integrate an open coding agent into the loop because it's less janky and then I'll have it try to fix the problem and propose a PR for me to review. If anyone else has used pi.dev or opencode or aider in this mode (completely non-interactive until the PR) I'd be curious to hear.
EDIT: Thank you to both responders. I'll just try the two options out then.
Is that an official term "coding harness"
Wondering if you wanted a similar interface (though a GUI not just CLI) where it's not for coding what would you call that?
Same idea cycle through models, ask question, drag-drop images, etc...
there is also pz a drop-in replacement for pi rewritten in Zig. 1.7MB static binary, 3ms startup, 1.4MB RAM idle. Find more at:
https://github.com/elyase/awesome-personal-ai-assistants?tab...
Pi ships with powerful defaults but skips features like sub-agents and plan mode
Does anyone have an idea as to why this would be a feature? don't you want to have a discussion with your agent to iron out the details before moving onto the implementation (build) phase?
In any case, looks cool :)
EDIT 1: Formatting EDIT 2: Thanks everyone for your input. I was not aware of the extensibility model that pi had in mind or that you can also iterate your plan on a PLAN.md file. Very interesting approach. I'll have a look and give it a go.
Note there is a fork oh-my-pi: https://github.com/can1357/oh-my-pi
of https://blog.can.ac/2026/02/12/the-harness-problem/ fame. I use it as a daily driver but I also love pi.
What models are you all using with Pi? How much are you paying on monthly or weekly basis for your usage? I'm very interested in it, but my budget is constrained and the usage granted by a $20/month Claude plan seems much more affordable than when I've tried API-based access with other agents. Unfortunately, this locks me in to Claude Code.
Coming from OpenClaw, it's pretty amazing how fast pi is, particularly paired with Qwen3 that dropped today. It's a magical time.
I’m working with a friend to build an ui around Pi to make it more user friendly for people who prefer to work with a gui (ala conductor). You can check out the repo: https://github.com/philipp-spiess/modern
What are people using to cost efficiently use this? I was using a Google Ultra sub which gave enough but that’s gone now.
ChatGPT $20/month is alright but I got locked out for a day after a couple hours. Considering the GitHub pro plus plan.
What's a coding harness? Claude Code is a "harness" and not a TUI?
Stop advertising pi, people. It _somehow_ continued to fly somewhat under the radar after that whole OpenClaw nonsense. Don’t make Anthropic’s sic their bloodhounds on them like they did on OpenCode.
Interesting approach to planning via extensions. I took a similar direction with enforcement. A governance loop that hooks into the agent's tool calls and blocks
execution until protocol is followed. Every 10 actions (configurable), the agent re-centers. No permission popups, but the agent literally can't skip steps.
Open source: https://github.com/isagawa-co/isagawa-kernel
The people pushing oh-my-pi seem to have missed the point of pi... Downloading 200k+ lines of additional code seems completely against the philosophy of building up your harness, letting your agent self-improve, relying on code that you control.
If you want bags of features, rather clone oh-my-pi somewhere, and get your agent to bring in bits of it a time, checking, reviewing, customising as you go.
100% this is where OpenCode missed the boat.
PI is what it looks like when you treat your Plugin sdk as the golden path
I do not understand some of the comments here: openclaw uses pi.
It seems stange also that even Steinberger in his interviews is not giving pi the proper attribution.
Anyone managed to run pi in a completely sandboxed environment? It can only access the cwd and subdirectories
too bad I cannot star this..
https://github.com/badlogic/pi-mono/tree/main/packages/codin...
The way you’re able to extend the harness through extension/hook architecture is really cool.
Eg some form of comprehensive planning/spec workflow is best modeled as an extension vs natively built in. And the extension still ends up feeling “native” in use
I recently discovered this via a YouTube video a few days ago
I really like the customization aspect of it and you can build tools on fly and even switch model mid session
There’s another project here called oh my pi has anyone here tried it
ive been using pi for about a week as daily driver and so far im happy with it. I really like the modular concept and also that its rather minimal
I’ve been testing it for a few days on pretty much clean install (no customizations/extensions) and it’s ok. Not sure if I like it yet.
Anyone tried pi with 5.3-codex vs codex cli?
Pi treats you like an adult and shows whatever the fuck LLM is doing rather than actively hiding shit from the user. And just for that, once you tasted the freedom and transparency, there’s no way to go back to CC.
This domain must have costed $$$$
too many things named ‘pi’, kmn
But I can't use my Codex plan with it, right? I have to use an API key?
Naming skills though...