HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
earendil-works
pi
TypeScript2025–2026
earendil-works / pi

pi

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

82Distinct people
101Mentions
2Explicit recommenders
121.7KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

GitHub

Where it is used

  • OpenClaw — OpenClaw embeds the Pi SDK to run an AI coding agent inside its messaging Gateway. It uses Pi’s createAgentSession-based runtime to control sessions, tools, and streaming without external processes. Source

What people are saying

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

manoji used a recommendation phrase. 2 indexed comments match. This is a phrase match, not a verdict.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 6:28:55 AM UTC.

Pi: Virtual Models direct repository link

Read the discussion on HN. A full-thread summary is not available yet.

Mentions over time

HN mentions by month101 dated mentions

Observed mentions: 2025-11-16 20:54:39 UTC to 2026-10-29 13:42:01 UTC.

01020302025-11-01 00:00:00 UTC to 2025-12-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsNov 20252025-12-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-01-01 00:00:00 UTC to 2026-02-01 00:00:00 UTC (exclusive): 5 mentions; 4 submissions, 1 comments2026-02-01 00:00:00 UTC to 2026-03-01 00:00:00 UTC (exclusive): 28 mentions; 4 submissions, 24 comments2026-03-01 00:00:00 UTC to 2026-04-01 00:00:00 UTC (exclusive): 8 mentions; 2 submissions, 6 comments2026-04-01 00:00:00 UTC to 2026-05-01 00:00:00 UTC (exclusive): 10 mentions; 0 submissions, 10 commentsApr 20262026-05-01 00:00:00 UTC to 2026-06-01 00:00:00 UTC (exclusive): 6 mentions; 0 submissions, 6 comments2026-06-01 00:00:00 UTC to 2026-07-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-07-01 00:00:00 UTC to 2026-08-01 00:00:00 UTC (exclusive): 8 mentions; 0 submissions, 8 comments2026-08-01 00:00:00 UTC to 2026-09-01 00:00:00 UTC (exclusive): 13 mentions; 4 submissions, 9 comments2026-09-01 00:00:00 UTC to 2026-10-01 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments2026-10-01 00:00:00 UTC to 2026-11-01 00:00:00 UTC (exclusive): 16 mentions; 2 submissions, 14 commentsOct 2026

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Nov 20252025-11-01 00:00:00 UTC2025-12-01 00:00:00 UTC101
Dec 20252025-12-01 00:00:00 UTC2026-01-01 00:00:00 UTC101
Jan 20262026-01-01 00:00:00 UTC2026-02-01 00:00:00 UTC541
Feb 20262026-02-01 00:00:00 UTC2026-03-01 00:00:00 UTC28424
Mar 20262026-03-01 00:00:00 UTC2026-04-01 00:00:00 UTC826
Apr 20262026-04-01 00:00:00 UTC2026-05-01 00:00:00 UTC10010
May 20262026-05-01 00:00:00 UTC2026-06-01 00:00:00 UTC606
Jun 20262026-06-01 00:00:00 UTC2026-07-01 00:00:00 UTC101
Jul 20262026-07-01 00:00:00 UTC2026-08-01 00:00:00 UTC808
Aug 20262026-08-01 00:00:00 UTC2026-09-01 00:00:00 UTC1349
Sep 20262026-09-01 00:00:00 UTC2026-10-01 00:00:00 UTC404
Oct 20262026-10-01 00:00:00 UTC2026-11-01 00:00:00 UTC16214

What Hacker News says

28 sources
Every proprietary harness is just proprietary junk without ability to extend it without polluting context. This includes claude-code, gemini-cli, codex etc. They have tools which hardcode the behavior that is impossible to modify, they add tools you may not need that pollute context, they inject an entire textbook's worth of words into the system prompt which pollutes context, they provide zero observability into what the agent is doing when it's launching a subagent as one example. They don't provide easy way to use multiple models from multiple providers for varying tasks. One model may be the best thing on earth at one thing, but fail miserably for another. Try orchestrating multiple agents from claude, gemini and codex in any of these proprietary boxes. They also... suck at TUI UX. I don't know if it was fixed already, but claude code
Read the rest
had flickering issue that was unresolved for more than a year. You need to take a very good care of what goes into your context. A black box of proprietary harnesses is not it. Check out pi [1] for example, which is a very minimal harness with really nice extension system. The idea is that you start with barebones and add things that you need for your own goals. claude-code HAS to have all these bells and whistles that pollute context to support larger audiences that can't tinker with it. If you have the ability to only pull in only what you need and extend things in a way that works for your workflow, you'll always get the best experience. And claude-code may never be that without making it complicated for the masses. OSS will always win here. [1] https://github.com/badlogic/pi-mono
In How will OpenAI compete?
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-mo... I am quite happy with my patched forks for now
In Pi – A minimal terminal coding harness
This looked interesting because I prefer rust over npm. The first issue I had was to figure out the schema of the models.json, as someone who hadn't used the original pi before. Then I noticed the documented `/skill:` command doesn't exist. That's also hard to see because the slash menu is rendered off screen if the prompt is at the bottom of the terminal. And when I see it, the selected menu items always jumps back to the first line, but looks like he fixed that yesterday. The tool output appears to mangle the transcript, and I can't even see the exact command it ran, only the output of the command. The README is overwhelmingly long and I don't understand what's important for me as a first time user and what isn't. Benchmarks and code internals aren't too terribly relevant to me at this point. I looked at the original pi next and realize
Read the rest
d the config schema is subtly different (snake_case instead of camelCase). Since it was advertised as a port, I expected it to be a drop-in replacement, which is clearly not the case. All in all it doesn't inspire confidence. Unfortunate. Edit: The original pi also says that there is a `/skill` command, but then it is missing in the following table: https://github.com/badlogic/pi-mono/tree/main/packages/codin... The `/skill` command also doesn't seem registered when I use pi. What is going on? How are people using this? Edit2: Ah, they have to be placed in `~/.pi/agent/skills`, not `~/.pi/skills`, even though according to the docs, both should work: https://github.com/badlogic/pi-mono/tree/main/packages/codin... This is exhausting.
In Pi – A minimal terminal coding harness
Would 1000% prefer to use Pi (https://github.com/badlogic/pi-mono) for building anything relating to AI agents. It's already battle-tested in super popular applications (like OpenClaw for example and many others), has 100s of extensions, is already built in a type-safe language, excellent community. And it also includes a full TUI and WebUI for interface support. Also Pydantic is a VC backed business now trying to funnel people into using their paid cloud services. No thanks.
In Build your own custom AI CLI with Pydantic AI
That's crazy that people are complaining the 'LLM writing style' and lack of content here. For me it reads very clear and succinct. Can I rewrite it with fewer words? Yes: > [Pi](https://github.com/badlogic/pi-mono/tree/main) is a minimal coding agent developed by Mario Zechner (libGDX's dev). I tried every ai coding tool from Cursor to Claude Code to Gemini CLI. But they're bloated with unnecessary system prompts and instructions. With Pi I saved 50% of my context window. It's open sourced and I believe it's the future! Is this the future you envision? An HN that looks like Twitter?
In The Engine Behind the Hype
grey-area·Feb 24, 2026Recommendation phrase
"The lobster gets the attention. The engine gets quietly forked into production." Is there any way to stop LLMs generating text like this? Is it really better than just writing it yourself? I guess generating blog posts is lower-effort and thus wins in this attention economy people think they are competing in. The actual engine is here: https://github.com/badlogic/pi-mono An interesting idea to have a bit more control over what your 'agent' is doing and keep it simple. Some of the prompts do give me pause though, why do we talk to text generators as if they are people, have we found this works best, or is it a sort of cargo-cult? https://github.com/badlogic/pi-mono/blob/main/.pi/prompts/is... I love that he's telling his tools not to trust people in his comments here!
In The Engine Behind the Hype
I saw this today on X. It's built on top of the pi coding agent (same one used by openclaw). It uses pi-web-ui ( https://github.com/badlogic/pi-mono/tree/main/packages%2Fweb...). What surprised me was that it works with oauth tokens from consumer AI subscriptions, and even free ones like Antigravity. Some of this is inherited from pi, but the author did some extra work to build a proxy to allow auth to work even from within the Excel sidebar. I'm not sure how it works and what the role of the backend is. But I hope to test it side by side with 'Claude for Excel', which I also happened to install today. (I tried both on something basic just to check they were installed correctly.)
In Pi for Excel: AI sidebar add-in for Excel
"The street finds its own uses for things" is getting to be vastly more true than it was! (And happy upcoming 40th birthday to Burning Chrome!!) I do hope that, even though individual software is not super valuable, that people find broader general systems that help them tie together their many disposable softwares, that their disposable softwares build off of. Just a hope. Seems like quick and dirty is winning, but having more platform underfoot that is reusable and durable and used frequently I think will be powerful. Pi as a self modifying platform is a very lo-fi version of this, is a self extending platform, which is amazing. https://github.com/badlogic/pi-mono https://lucumr.pocoo.org/2026/1/31/pi/ The suggestion to have APIs for your product to remain relevant in the new world is extremely good. It still requires understanding the
Read the rest
API world at least somewhat. I'd complement that suggestion here with a recommendation to try to lean in hard to webmcp, if you really want to help your users to find agentic success. WebMCP allows for contextual exposure of what the user is already seeing on the page, brings much more session context in that APIs typically do. That seamless blending of user experience & API/m2m control is enormously powerful for letting users go at things. https://webmachinelearning.github.io/webmcp/ https://news.ycombinator.com/item?id=47037501
In When interfaces become disposable
rnc000·Feb 16, 2026Submission

Show HN: Rakenne – Markdown-defined agentic workflows for structured documents

Hi! I’m the creator of Rakenne and I built it because I noticed a recurring problem with LLMs in professional settings: chat-based document creation is unpredictable and hard to scale for domain experts. Experts know the process of building a document (the questions to ask, the order of operations, the edge cases), but translating that into a long system prompt often leads to hallucinations or missed steps. What is Rakenne? Rakenne is a multi-tenant SaaS that lets domain experts define "Guided Workflows" in Markdown. An LLM agent then runs these workflows server-side, conducting a structured dialogue with the user to produce a final, high-fidelity document. The Tech Stack: * Agentic Core: Built on the pi coding agent (https://github.com/badlogic/pi-mono) using RPC mode. This allows the agent to maintain state and follow complex logic bran
Read the rest
ches defined in the Markdown files. * Frontend: Built with Lit web components. I wanted something incredibly lightweight and framework-agnostic so the document "interviews" feel snappy and can eventually be embedded as widgets. * Multi-tenancy: Designed to isolate agent environments server-side, ensuring that custom expert logic doesn't leak between tenants. Why this approach? Instead of "Chat with a PDF," it’s "The Logic of an Expert." If you’re a lawyer or a compliance officer, you don’t want a creative partner; you want a system that follows your proven methodology. By using Markdown, we make the "expert logic" version-controllable and easy for non-devs to edit. I’d love your feedback on: 1. The Agentic UX: Does the "interview" flow feel natural, or is it too rigid? 2. Markdown as Logic: Is Markdown the right "DSL" for this, or should we move toward something like YAML or a custom schema? 3. Latency: We're using RPC for the agent-browser communication—is the response time acceptable for your use case? Thanks! I'll be around to answer any technical questions.
2 points · Open discussion
I really hope Mario who wrote the engine that powers OpenClaw[0] gets spoils as well. OpenClaw is mostly a shell around this (ha!), and I've always been annoyed OpenClaw never credited those repos openly. The pi agent repos are a joy to read, are 1/100th the size of OpenClaw, and have 95% of the functionality. [0]: https://github.com/badlogic/pi-mono
In I’m joining OpenAI

Showing the 15 most recent of 28 sources. Enable JavaScript to search and browse every indexed mention.

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.