
Pi Coding Agent
CLI极简、可扩展的终端 AI Agent:可让它自己编写提示词模板、技能、扩展与主题,支持 print / JSON / RPC 模式供脚本调用,并提供 TypeScript SDK。需要 Node.js 22.19+。
New issues and PRs from new contributors are closed automatically. Maintainers review closed submissions daily. See CONTRIBUTING.md.
Pi
Pi is a minimal, extensible AI agent for the terminal. Adapt Pi to your workflow, not the other way around.
Ask Pi to create the prompt templates, skills, extensions, and themes you need, or install a Pi package. Use Pi directly, automate it in print, JSON, or RPC mode, or build applications with the TypeScript SDK.
Getting started
Install the command-line interface with npm:
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
This requires Node.js 22.19 or newer. Pi does not require dependency lifecycle scripts for a normal npm installation.
On macOS or Linux, you can instead use the installer:
curl -fsSL https://pi.dev/install.sh | sh
Start Pi in the directory where you want it to work:
cd /path/to/project
pi
For a built-in AI provider, run /login inside Pi to connect a subscription or API key. Then give Pi a task.
See the documentation for full setup and usage instructions.
Development
Clone the repository, install its dependencies, and run Pi from source:
git clone https://github.com/earendil-works/pi
cd pi
npm install --ignore-scripts
./pi-test.sh
pi-test.sh can be called from any directory and preserves the caller's working directory.
Before submitting changes, run:
npm run check
./test.sh
Read CONTRIBUTING.md before opening an issue or pull request. It defines the contribution gate, issue quality bar, and required checks. Read AGENTS.md for repository-specific implementation, testing, dependency, and release rules.
License
MIT
相关资源

goose
CLI在本机运行的通用 AI Agent,提供桌面端、CLI 与 API,Rust 实现,可接入 15+ 家模型供应商并通过 MCP 连接 70+ 扩展;源自 Block,现属 Linux 基金会旗下 AAIF。
aaif-goose/goose54.7k
MCPorter
CLI在终端和脚本里发现、调用 MCP 服务器的命令行与 TypeScript 运行时:列出工具签名并直接调用工具,还能把 MCP 服务器生成独立 CLI 或类型化客户端;会自动导入 Claude Code、Codex 等已有的 MCP 配置。
openclaw/mcporter5k
MCP Builder
Skill指导 agent 构建高质量 MCP 服务器:调研协议与目标 API、设计工具、用 Python(FastMCP)或 TypeScript SDK 实现,并编写评测问题验证效果。Anthropic 官方技能。
anthropics/skills179k
Agent SDK Dev
Plugin用 /new-sdk-app 交互式搭建 Claude Agent SDK 项目(Python 或 TypeScript),再由校验代理按官方最佳实践检查依赖、配置与代码。Anthropic 官方维护。
anthropics/claude-code150k
Plugin Dev
Plugin开发 Claude Code 插件的工具包:7 个技能覆盖插件结构、钩子、MCP 集成、命令、子代理与技能编写,附八阶段引导式创建命令,以及代理生成、插件校验、技能评审三个子代理。Anthropic 官方维护。
anthropics/claude-code150k
Ruflo
Plugin面向 Claude Code 与 Codex 的多代理编排框架(原 Claude Flow):蜂群协作、自学习记忆与跨机器联邦通信;插件市场提供 30 余个插件,完整功能需 npx ruflo init 安装。
ruvnet/ruflo74.1k