earendil-works/pi

I suspect heavy eyes free coding. I spent the last week helping them understand a major security regression in config loading, took two issues/pull requests. Our hunch is the Ai told them what they had was good, not enough human critical thinking. https://news.ycombinator.com/item?id=50075319 I've switched to Pi because I do not like the direction v2 has taken UX. Nor do I trust the security posturing going forward. There is also the social media stunts of the CEO that push me away. I'm now trying to advocate Pi adopt system level configuration for similar security reasons. If any HNers would like to add their thoughts, please do so here https://github.com/earendil-works/pi/issues/10895

Pi [1] is amazing. Since using it I've felt no need to switch harnesses anymore. Or choose Oh My PI [2] for batteries included [1] https://github.com/earendil-works/pi [2] https://github.com/can1357/oh-my-pi

I love Pi . I have been building an agent using its agent harness https://github.com/earendil-works/pi/tree/main/packages/agent . I love the simplicity .

Pi is really good. For people who want to build their own agent with even more minimal and extensible, the underlying agent harness is also worth looking: https://github.com/earendil-works/pi/tree/main/packages/agent/src/harness

I replaced Raycast recently with Sol[0], but SuperCmd[1] is also really good. And I’m testing Helium Browser[2]. It’s based on Chromium, but has changed a lot under the hood and I’ve been daily driving it. Also replacing CapCut with OpenCut[3]. I’ve also completely ditched Codex CLI with Pi[4] and now am trying OMP[5]. 0. https://github.com/ospfranco/sol 1. https://github.com/SuperCmdLabs/SuperCmd 2. https://github.com/imputnet/helium 3. https://github.com/OpenCut-app/OpenCut 4. https://github.com/earendil-works/pi 5. https://github.com/can1357/oh-my-pi

pi sends 1k (or less) -> https://github.com/earendil-works/pi/blob/main/packages/coding-agent/src/core/system-prompt.ts My $20 sub using gpt 5.6 sol thinking-off lasts for hours using pi.

To all the haters to not knowing what "pi" means in this context. Is mario zechner's ai agent / coding harness [1][2], similar in spirit albeit much less complex to claude code or openai's codex and others. I wouldn't call it third tier. If anything alongside opencode, and codex, its one of the "first tier" and the only non-VC-backed (at least before mario joined earendil (idk about earendil raising or not) anyways. Pi is good. I dont need a telegram client for it, but this precisely show why pi is great, because its really easy to extend pi building plugins or modifying the source (yay, open source) peace 1. https://github.com/earendil-works/pi 2. https://pi.dev/

My point is pi-coding-agent [1] is a very well designed and implemented open source project that we all can learn from as software engineers. His blog post about his decision making [2] is also very well written. I should've given original links instead of noisy HN threads. [1] https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/README.md [2] https://mariozechner.at/posts/2025-11-30-pi-coding-agent/ pi-conding-agent itself is not a product yet and it won't have much value to end users other than those using the products built on top of it.

Big +1 to Pi[1]. The simplicity makes it really easy to extend yourself too, so at this point I have a pretty nice little setup that's very specific to my personal workflows. The monorepo for the project also has other nice utilities like a solid agent SDK. I also use other tools like Claude Code for "serious" work, but I do find myself reaching for Pi more consistently as I've gotten more confident with my setup. [1] https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent

We may both be partially right, the main dev I interacted with has Tel Aviv on his GitHub (also 'Hanna' being around the project, but apparently that is a surname not a first name, and a mistaken extrapolation on my part) https://github.com/davidbrai https://github.com/earendil-works/pi/issues/10895 The lack of professionalism or seriousness was mainly in a private email chain with Armin. He added a single comment to this issue after that chain which was the gist of a couple of his replies, less snarky. Either way, the interaction left me disappointed, not a founder who seems interested in listening or learning imo.

…nough to sandbox pi.dev, because remember, it's a minimalist coding agent! So what does a minimalist coding agent do? Of course! It loads extensions by default and do you know what extensions can do? they can add default tools that bypass --no-tools! So if you want to sandbox your agent, guess what you'll have to do? Yep, you have to supply --no-extensions. Here is how to run pi.dev under its most minimal configuration under a sandbox: pi --no-tools --no-extensions --tools tool1, tool2, tool3 -e ./your-sandboxing-extension Pretty neat, huh? Sources: https://github.com/earendil-works/pi/issues/555

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#discussioncomment-15827978 And another other thing I fixed …

I suggest you make yourself a private fork of Pi so that you don't have to be beholden to Mario and his not-so-new clique. Create a private repo in GitHub first, then do a bare Git clone of https://github.com/badlogic/pi-mono.git (ideally do it before the original repo gets moved to Earendil's GitHub org). git clone --bare https://github.com/badlogic/pi-mono.git then push that bare clone up to your private repo: git push --mirror <url of your private repo> Afterwards, delete that bare clone and clone your new private repo, then set upstream to the original badlogic/pi-mono repo: git remote add upstream https://github.com/badlogic/pi-mono.git How long you want to continue pulling from …

I use a sandbox example extension with comes with Pi, it uses the anthropic sandbox runtime (bubblewrap on linux). The runtime has one bug and needs one improvement (I've made PRs, no response yet). Pi's sandbox example extension does not block internal tools (read/write) according to rules, I've created a PR but can't submit because of Pi's OSS vacation BS... https://github.com/badlogic/pi-mono/compare/main...k3a:pi-mono:sandbox-tool-patterns I am quite happy with my patched forks for now