Claude Skill
rawwerks/ypi
ypi 是一种受递归语言模型(RLMs)启发的递归编码代理。通过 CLI 自主生成、优化和执行代码,适用于代理和迭代开发工作流。
概览
仓库信息
安装这个 Skill
npm install -g ypiRegistry 信息
npm install -g ypinpx ypi "What does this repo do?"git clone https://github.com/rawwerks/ypi.git && cd ypi
项目简介
ypi 是一种受递归语言模型(RLMs)启发的递归编码代理。它提供 CLI 工具,利用递归自主生成、优化和执行代码,专为代理工作流和迭代开发而设计。
A recursive coding agent inpired by RLMs
要点
- 受递归语言模型(RLMs)启发的递归代码生成
- 基于 CLI 的自主编码代理
- 对生成代码进行迭代优化
- 轻量级 Shell 实现
- 专为代理和递归工作流设计
使用场景
- 自动化代码生成与调试
- 迭代式软件开发任务
- 使用递归 AI 代理进行原型设计
- 面向开发者的 CLI 编码助手
- 探索受 RLM 启发的代理架构
README 摘要
# ypi [](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