Hacker News Reader

Comment by ElFitz | Hacker News Reader

Has anyone (other than OpenClaw) used pi? (https://shittycodingagent.ai/, https://pi.dev/)

Any insights / suggestions / best practices?

Its really fantastic. I can't imagine why you'd go through the effort using Claude Code with other models when pi is a much better harness. There's tons of extensions already available, and its trivial to prompt an LLM to create your any new extension you want. Lacking creativity and want something from another harness?

> Run <other harness> in tmux and interrogate it how feature X works, then build me the equivalent as a pi extension.

Maybe in a few years there will be obvious patterns with harnesses having built really optimal flows, but right now it works so much better to experiment and try new approaches and prompts and flows, and pi is the easiest one to tweak and make it your own.

> but right now it works so much better to experiment and try new approaches and prompts and flows, and pi is the easiest one to tweak and make it your own.

That’s what really appeals to me. I’ve been fighting Claude Code’s attempts to put everything in memory lately (which is fine for personal preferences), when I prefer the repo to contain all the actual knowledge and learnings. Made me realise how these micro-improvements could ultimately, some day, lead to lock-in.

> Run <other harness> in tmux and interrogate it how feature X works, then build me the equivalent as a pi extension.

I’ll give it a try!

Yes, it's super cool. Check Mario's latest talk: https://www.youtube.com/watch?v=Dli5slNaJu0 Armin also has some videos covering it on his channel: https://www.youtube.com/@ArminRonacher/ Pi's Discord is still nice, even though it was a bit flooded after the openclaw thing.

I really love it. The simplicity is key. The first play project I made with it was a public transport map with GTFS data - click on a stop and get the routes and the timetables for the stop and the surrounding ones. I used Qwen3.5-35B on Mac M1 Max with oMLX. It wrote 98% of the code with very little interaction from me. And very useful is the /tree feature to go back in history when the model is on a wrong track or my instructions where not good enough. I usually work in a two path approach: first let the model explore what it needs to fulfill the task and write it into CONTEXT.md (or any other name to your liking). Then restart the session with the CONTEXT.md. That way you are always nicely operating in 5-15k context, i.e. all is very fast. Create an account for pi (or docker) and make sure it can't walk into other directories - it has bash access. Add the browser-tools to the skills and load them when useful: https://github.com/badlogic/pi-skills

No need for database MCP, I use postgres and tell it to use psql.

Occasionally I use prettier to remove indentation - the LLM makes a lot less edit errors that way. Just add the indent back before you commit. Or tell pi to do it.

had been using claude max/opus with pi and the results have been incredible. Having pi write an AGENTS.md and dip your feet into creating your own skills specific to the project.

With the anthropic billing change (not being able to use the max credits for pi) I think I have to cancel - as I'm whirring through credits now.

Going to move to the $250/mo OpenAI codex plan for now.

Regardless of which harness you use, asking your agent to self-edit its own .claude (and to put it in the repo itself so you see the changes) is the single biggest impact change you can make in terms of compounding improvement. Couple this with telling it to create skills for /garden (clean up drift based on what changed this session), /handoff (garden, create ant skills to resolve friction encountered this session, and write a summary of the session and note for next agent), /takeover (read the latest handoff file). Since doing this I’ve completely cured my session-abandonment anxiety and can confidently swap to a new session at < 20% context usage without feeling like I’m talking to someone who just woke up from a coma.

Can you provide more details on these skills?

Honestly… just paste my comment into the prompt and you’ll get it 80% of the way there. The important thing is to seed it with instructions so it will iteratively improve its own instructions each session.

I was looking into this as well since Claude models are costing too much with the Extra Usage changes.

Is OpenAI codex not also charging by usage instead of subscription when using pi?

pi is what OpenClaw runs on, and so far OpenAI seems committed to it. No telling how long it will last.

Pi is a lot simpler than Claude and a lot more transparent in how it operates.

It's designed to be a small simple core with a rich API which you can use for extensions (providing skills, tools, or just modifying/extending the agent's behaviour).

It's likely that you'll eventually need to find extensions for some extended functionality, but for each feature you can pick the one that fits your need exactly (or just use Pi to hack a new extension).

I bought a $30 Z.ai Coding Plan sub to go with it. 7 million tokens has only gone through 2% of my weekly usage using the GLM-5.1 model. I am pretty happy.

I am only doing single project workflows, but with Z.ai I feel like it opens a whole new door to parallel workflows without hitting usage limits.

Is GLM-5.1 actually good?

I tested one of the other models that everyone is raving about yesterday (Qwen 3.6 plus) and within minutes found myself arguing with it even over a very simple task. After about 30 minutes (in which token usage never went over 50k because it was just me rewinding to give it more and more explicit instructions which it kept ignoring), I reverted everything and did it with Opus in literally about 4 minutes, after intentionally giving Opus a much more vague prompt.

I've had a good experience so far. Idk if I would attribute that to Pi or the GLM models. However, it feels nice not being constrained by usage.

Yeah, that's pretty much the lines I was thinking along. Perhaps use codex for planning / reviews, but otherwise go with z.ai / minimax for actual implementation. Thanks!

i really have been enjoying pi a lot

at first i thought i was goring to build lots of extra plugins and commands but what ended up working for me is:

- i have a simpel command that pulls context from a linear issue

- simple review command

- project specific skills for common tasks

I use Daniel Meissler’s PAI and it’s been an incredible harness.

Reluctantly, the dev seems to have a stinky attitude.

He went on an "OSS vacation", which is perfectly reasonable and said he'd be back on a certain date. I had a PR open for a trivial fix, someone asked when it would land. I shared he was still away. After his return I politely asked, "@badlogic hey, what can we do to progress this? Thanks x"

I then got what I would consider an abusive reply, because he confused me with someone else. In the meantime he extended his vacation. Didn't even think his shitty attitude was worthy of an apology, that HE confused me with someone else.

https://github.com/badlogic/pi-mono/discussions/1475#discuss...

And another other thing I fixed with no attribution, just landed it himself separately. https://github.com/badlogic/pi-mono/discussions/1080

and

https://github.com/badlogic/pi-mono/issues/1079#event-223896...

Now he's seemingly marked anything with my name on as a "clanker", despite all my changes being by hand.

I've been around open source enough to have a thick skin, but when i'm doing something "for fun" and someone treats you like that, i'd rather avoid it as far as possible. I certainly could not in good faith use this project for anything work related.

> Honestly, it seems you are grumpy, so it was probably a good idea to extend that vacation. Being rude just creates a more toxic environment for everyone. Maybe extend that break for the rest of the month and come back nicer? Thanks

Honestly, it seems like both of you were feeling a bit "grumpy" at the moment, but sending passive aggressiveness towards the maintainer you are trying to get to merge your code (or not your code, someone else's code?) seems like a very bold strategy regardless.

You know, when I wrote that I genuinely meant it, or at least I think i did. It wasn't supposed to be passive aggressive. :(

But that doesn't negate the maintainer talking to people like that (and taking contributions without attribution).. and the net result is I don't want to use the software, and frankly they probably won't miss me.. so the end result is neutral.. I just find it sad.

> Maybe extend that break for the rest of the month and come back nicer?

Quite sure most (perhaps >99%) adult people would consider this passive aggressive.

But yeah, I agree with you for the rest part. Why did Mario assume that bot is you...?

if a human showed up directly under some bot bullshit pinging me I'd assume they were the bot operator as well

I'm not sure how you'd be able to interpret that as anything other than passive aggressive.

> You know, when I wrote that I genuinely meant it, or at least I think i did. It wasn't supposed to be passive aggressive. :(

That's a great opportunity for self reflection.

Yeah, I take that. I've thought about it much of this evening.

I think at the time I was frustrated, it felt unfair and I couldn't understand it.

Then I thought,this guy probably does need more time off. Which was a genuine thought.

But that is where I should have stopped. The way i expressed it, whilst genuine thought, was expressed in a way which was passive aggressive. I am owning that.

> Then I thought,this guy probably does need more time off. Which was a genuine thought.

The thought was correct, he was probably stressed. You made it worse.

> The way i expressed it, whilst genuine thought, was expressed in a way which was passive aggressive

The way you expressed is a technicality, what counts here was your action.

Open source developers owe you nothing, you can always fork and implement your feature by yourself.

Behaving the way you did, treating it as something about you, is very selfish.

I've acknowledged everything you've said previously. Now why do you feel the need to continue it?

But I will add, they may have had a bad day, but that doesn't give the maintainer the freedom to be rude to others.

The fact is, I was polite, maintainer was rude, and I reacted badly to it and was worse.

But as you say, my choice was to not be further interested in the project... Which is what I said earlier.

You seem to have posted your polite question as a reply to the bot comment which talks about PR #1484 and not your PR. I'd say it's pretty obvious why the maintainer thought you were pushing the bot's PR.

As someone else pointed out cooler heads and less passive aggressive responses would've resolved this issue easily.

But hey, the dev was generous to give it an MIT license, you could always just fork it and what you like ¯\_(ツ)_/¯

Reply on news.ycombinator.com