i wrote the blog post and i also wrote pi.dev. i haven't written much code myself in the past 12 months. i'm not making coding agents out to be the problem. the entire last section keeps is basically "use a clanker for this and that".
i'm making specific usage pattersn out to be the problem, and explain why those patterns can't work due to the way agents work.
The better web UI is now part of https://github.com/rcarmo/piclaw (which is essentially the same, but with more polish and a claw-like memory system). So you can pick if you want TS or Python as the back-end :)
The claw version’s web UI essentially has better thinking output, more visibility of tool calls, and slightly better SSE streaming. I’ve backported some of it to vibes, but if you want to borrow UI stuff, the better bits are in piclaw. I use both constantly on my phone/desktop.
i'm not a member of openclaw.
i build some oss in parallel, and added 3 or so commits to the openclaw repo. and peter is taking some of the openclaw contributors with him.
peter's claw is a lot more than just a wrapper around my slop.
i too had plenty of offers, but so far chose not to follow through with any of them, as i like my life as is.
also, peter is a good friend and gives plenty of credit. in fact, less credit would be nice, so i don't have to endure more vibeslopped issues and PRs going forward :)
For me it is the simplicity of it (transparent minimal system prompts and harnest), you can extend it the way you like, I don't have to install a (buggy) Electron app (CC or Codex app), it integrates where I work, because it's simple (like in a standard terminal on VS code). I'm not locked in with any vendor and can switch models whenever I want, and most importantly, I can effectively use it within apps that are themselves using it as coding agent (the meta part - like a chat UI for very specific business cases). Being in TypeScript, it integrates very well with the browser and one can leverage the browser sandbox around it.
I cannot directly answer your question, because I am looking into this topic myself currently, but I found this HN discussion from two weeks ago, which should give you more insights about pi: https://hackertimes.com/item?id=46844822
FWIW, you can use subscriptions with pi. OpenAI has blessed pi allowing users to use their GPT subscriptions. Same holds for other providers, except Flicker Company.
And I'm personally very happy that Peter's project gets all the hype. The pi repo already gets enough vibesloped PRs from openclaw users as is, and its still only 1/100th of what the openclaw repository has to suffer through.
Good to know, that makes it even better. I still find Opus 4.5 to be the best model currently. But if next generation of GPT/Gemini close the gap that will cross the inflection point for me and make 3rd party harnesses viable. Or if they jump ahead, that should put more pressure on the Flicker Company to fix the flicker or relax the subscriptions.
Not only did you build a minimal agent, but the framework around it so anyone can build their own. I'm using Pi in the terminal, but I see you have web components. Any tips or creating a "Chat mode" where the messages are like chat bubbles? It would be easier to use on mobile.
i'm making specific usage pattersn out to be the problem, and explain why those patterns can't work due to the way agents work.
reply