Claude Skill

rawwerks/ypi

ypi is a recursive coding agent inspired by RLMs. Use its CLI to autonomously generate, refine, and execute code for agentic and iterative development workflows.

Overview

Stars339
Forks29
LanguageShell
Last pushed2026-06-16
Last synced2026-06-17
View on GitHub

Repository

Ownerrawwerks
Repositoryypi
Full namerawwerks/ypi
Repo ID1,154,014,971

Install this Skill

npm install -g ypi

Registry

Typeopenclaw_skill
Quality score80/100
Verificationreadme_parsed
Last verified2026-06-14
Platforms
ClaudeOpenClaw
Capabilities
memorysearchterminalworkflowagentscliopenclawpirecursionrlm
Detected files
README.mdpackage.jsontests
Config keys
PACKAGE_JSON
Install methods
  • npm install -g ypi
  • npx ypi "What does this repo do?"
  • git clone https://github.com/rawwerks/ypi.git && cd ypi

Summary

ypi is a recursive coding agent inspired by Recursive Language Models (RLMs). It provides a CLI tool that leverages recursion to autonomously generate, refine, and execute code, designed for agentic workflows and iterative development.

Chinese description

一种受递归语言模型(RLMs)启发的递归编码代理

Key features

  • Recursive code generation inspired by RLMs
  • CLI-based agent for autonomous coding tasks
  • Iterative refinement of generated code
  • Lightweight Shell implementation
  • Designed for agentic and recursive workflows

Use cases

  • Automated code generation and debugging
  • Iterative software development tasks
  • Prototyping with recursive AI agents
  • CLI-based coding assistant for developers
  • Exploring RLM-inspired agent architectures

README excerpt

# ypi [![npm](https://img.shields.io/npm/v/ypi?style=flat-square)](https://www.npmjs.com/package/ypi) **ypi** — a recursive coding agent built on [Pi](https://github.com/badlogic/pi-mono). Named after the [Y combinator](https://en.wikipedia.org/wiki/Fixed-point_combinator#Y_combinator) from lambda calculus — the fixed-point combinator that enables recursion. `ypi` is Pi that can call itself. (`rpi` already has another connotation.) Inspired by [Recursive Language Models](https://github.com/alexzhang13/rlm) (RLM), which showed that an LLM with a code REPL and a `llm_query()` function can recursively decompose problems, analyze massive contexts, and write code — all through self-delegation. ## The Idea Pi already has a bash REPL. We add one function — `rlm_query` — and a system prompt that teaches Pi to use it recursively. Each child gets its own [jj](https://martinvonz.github.io/jj/) workspace for file isolation. That's the whole trick. ``` ┌──────────────────────────────────────────┐ │ ypi (depth 0) │ │ Tools: bash, rlm_query │ │ Workspace: default │ │ │ │ > grep -n "bug" src/*.py │ │ > sed -n '50,80p' src/app.py \ │ │ | rlm_query "Fix this bug" │ │ │ │ │ ▼ │ │ ┌────────────────────────────┐ │ │ │ ypi (depth 1) │ │ │ │ Workspace: jj isolated │ │ │ │ Edits files safely │ │ │ │ Returns: patch on stdout │ │ │ └────────────────────────────┘ │ │ │ │ > jj squash --from <child-change> │ │ # absorb the fix into our work

Topics

Explore more

Data from GitHub. Synced on 2026-06-17