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 haven’t met a single person who has tried pi for a few days and not made it their daily driver.

Pleased to meet you!

For me, it just didn’t compare in quality with Claude CLI and OpenCode. It didn’t finish the job. Interesting for extending, certainly, but not where my productivity gains lie.

People seem to be really enjoying rolling everything themselves these days...

I've spent way too long working around the jank and extra features in Other People's Software.

Now I can just make my own that does exactly what I want and need, nothing more and nothing less. It's just for me, it's not a SaaS or a "start-up" I'm the CEO of.

That seems to be what a significant chunk of the "insane productivity" is actually going into

Because it’s very easy todo nowadays. Why making compromises in your workflow anymore?

Remember that OpenAI ran statistics on ChatGPT conversations and found development related conversations were in the low 10s https://openai.com/index/how-people-are-using-chatgpt/ - the people who enjoy rolling everything these days is representative of our echo-chamber.

Seriously? The most common complains on HN is how every software is built upon Electron and React.

What self-built capabilities do you like the most that claude code doesn't offer?

Not the person you replied to, but I'll stress the point that it is not just what you can add that Claude Code doesn't offer, but also what you don't need to add that Claude Code does offer that you don't want.

I dislike many things about Claude Code, but I'll pick subagents as one example. Don't want to use them? Tough luck. (AFAIK, it's been a while since I used CC, maybe it is configurable now or was always and I never discovered that.)

With Pi, I just didn't install an extension for that, which I suspect exists, but I have a choice of never finding out.

You can just put "Never use subagents" in your CLAUDE.md and it will honor it, no?

IME CLAUDE.md rarely gets fully honored. I've left HN comments before about how I had to convert some CLAUDE.md instructions to pre-commit deterministic checks due to how often they were ignored. My guesstimate is that it is about 70 % reliable. That's with Opus 4.5. I've since switched to GPT-5.2 and now GPT-5.3 Codex and use Codex CLI, Pi and OpenCode, not CC, so maybe things have changed with a new system prompt or with the introduction of Opus 4.6.

This is and has always been trivially configurable. Just put `Task` as a disallowed tool.

"hey, build a connector for z.ai GLM-5"

Can't do that with Claude =)

Claude code includes a large system prompt with every request while tool like pi does not. This could save tokens resulting in lower costs.

It sounds like it is the neovim or Emacs of coding agents.

I came here to say the same thing. It's basically _is_ Emacs. Heavily configurable tool, text-focused UI, primary interaction with a minibuffer ..er.. box to prompt at the bottom of the screen, package distribution mechanism, etc etc.

With Emacs modes like agent-shell.el available and growing, why not invest in learning a tool that is likely to survive and have mindshare beyond the next few months?

I've been using codex for about 2 months now and am pretty happy with it. What does pi do better than codex?

If you ever want to use other models, pi can do that. In the middle of a session I might switch from gpt-5.2 to opus and get it to do something or review something and then switch back to gpt. Since models are being released every few weeks this is interesting to compare models without having to switch to a different harness.

And if there’s any feature codex has that you want, just have pi run codex in a tmux session and interrogate it how said feature works, and recreate it in pi.

maybe one day

track changes is the big one to get right

i'll prob add over wkd hadn't bothered as still making changes

yes felt long overdue for OSS :)

I might do once I get local to a good spot. Should in theory be fine on web... but haven't tested/tried

Works surprisingly well, even the connection to local host to use my codex sub, would have not thoughts thats possible ;) Really cool work!

opencode is great, but I'm a big pi fan - pi has a minimal core that is hackable+extensible by design and is aware of its own docs. So your coding agent can mod your coding agent exactly as you like. https://pi.dev/

I’m building it

It’s got various things to clean up but the idea is to bring the spirit of pi (an OSS coding agent that can extend itself and gives you maximal freedom) to excel.

So it has things that claude for excel will never have - like tmux, the ability to use any model provider that works with pi, and of course extensions

built in lets you play snake while your agent works; I added some personal ones for slash commands, auto-pulling fx, ..

And nice touches like user and file agents.md

still quite a lot of work I need to juggle with my new job, but I’ve been using it all week with decent results

Quick doubt: did you modify Pi to make it browser compatible?

1. If yes, does it understand skills?

2. If it does have skills support, how are skills fed into it in a browser environment (without the filesystem, folders and stuff)

Didn't have to modify. OG Pi is made to be extended & used as a building block so closer to say I wrapped it As for skills, yes and it's a virtual filesystem

Just tried it, very cool! Do you have experience with limits, like is there a max table size it can reason about?

generally been fine, adding some optimisations over wkd to increase. Primary thing I want to fix = right now full tool results get passed direct into context so can overflow if using python on a large sheet

https://github.com/tmustier/pi-for-excel/issues/377