jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
pi-config
A curated, one-click installable configuration pack for the Pi coding agent, featuring 17 plugins, 18 global skills, and 2 MCP servers to enhance multi-agent collaboration, token efficiency, and browser automation.
Stars
100
7-day growth
No data
Forks
3
Open issues
0
License
MIT
Last updated
2026-07-25
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It turns Pi into a powerful multi-agent coding assistant with AST-level code intelligence, persistent memory, and a full browser automation suite, all provided as a copyable, documented template.
Who it is for
- Pi coding agent users seeking advanced capabilities
- Developers who want a pre-configured, production-ready agent environment
- Open-source enthusiasts interested in Pi's extension ecosystem
Use cases
- Run complex multi-step software development workflows delegated to sub-agents
- Perform in-depth code analysis and refactoring with AST-grep and LSP diagnostics
- Automate browser testing and web scraping with Playwright
- Maintain persistent project knowledge across chat sessions with memory
Strengths
- Comprehensive: 17 plugins, 18 skills, and 2 MCP servers cover almost every common coding agent need
- Efficient: context-mode plugin dramatically reduces token consumption by routing large outputs through a sandbox
- Easy setup: single bash script installs all plugins and merges MCP config
- Well-documented: every plugin and skill is explained with source links and usage notes
Considerations
- Requires a working Pi installation and manual API key configuration
- Some plugins (e.g., chrome-devtools MCP) require additional local binaries that must be configured per machine
- The configuration is opinionated; users may need to adjust tool active/inactive settings to suit their workflows
README quick start
我的 Pi Coding Agent 配置
██████╗ ██╗ ██████╗ ██████╗ ███╗ ██╗███████╗██╗ ██████╗
██╔══██╗██║ ██╔════╝██╔═══██╗████╗ ██║██╔════╝██║██╔════╝
██████╔╝██║ ██║ ██║ ██║██╔██╗ ██║█████╗ ██║██║ ███╗
██╔═══╝ ██║ ██║ ██║ ██║██║╚██╗██║██╔══╝ ██║██║ ██║
██║ ██║ ╚██████╗╚██████╔╝██║ ╚████║██║ ██║╚██████╔╝
╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═════╝
17 plugins · 18 global skills · 2 MCP servers · one-line installer
一份可直接复刻的 Pi 配置，整理成教程形式分享。包含 17 个插件、18 个全局 Skill、2 个 MCP server，配一键安装脚本。
仓库里的每样东西都经过实际使用筛选，目标是把 Pi 打造成一个能多代理协作、能省 token、能跑浏览器的全能终端编码代理。
一、Pi 是什么？
Pi（npm 包 @earendil-works/pi-coding-agent）是一个开源的终端 AI 编码代理。你给它一个任务，它在你本地的项目里读写文件、跑命令、调用工具来完成任务。
如果你还没装 Pi，先：
npm install -g @earendil-works/pi-coding-agent
然后跑 pi 进入交互界面。本仓库的所有插件都假设你已经有一个能正常工作的 Pi。
二、Pi 的整体架构
理解架构有助于你挑选和编写插件。Pi 是一个插件驱动的代理循环，核心分层：
┌─────────────────────────────────────────────────────┐
│ TUI / RPC / Print ← 用户交互层（终端界面 / API） │
├─────────────────────────────────────────────────────┤
│ Agent Loop ← 代理循环：收 prompt → 调模型 │
│ → 执行工具 → 回传结果 │
├─────────────────────────────────────────────────────┤
│ Providers / Models ← 多模型抽象：OpenAI / Anthropic │
│ / 本地 / 自定义 provider │
├─────────────────────────────────────────────────────┤
│ Tools ← 模型可调用的工具：bash/read/ │
│ edit/web_search/mcp/自定义 │
├─────────────────────────────────────────────────────┤
│ Extensions ← TypeScript 模块，能订阅事件、 │
│ 注册工具/命令/快捷键/主题 │
├─────────────────────────────────────────────────────┤
│ Skills / Prompts ← Markdown 形式的「过程知识」， │
│ 按需注入到模型上下文 │
├─────────────────────────────────────────────────────┤
│ Themes ← JSON 配色方案 │
├─────────────────────────────────────────────────────┤
│ Packages ← 上面这些资源的分发单位 │
│
Description
My Pi coding agent setup: 17 plugins + 18 global skills + 2 MCP servers, with a one-line installer and tutorial README.
Related repositories
Similar projects matched by category, topics, and programming language.
bjan
Featured
claudemux
Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.
AARomanov1985
Audio-Cassette-Simulation
A set of bash scripts using ffmpeg to simulate vintage cassette tape audio profiles with noise, wow/flutter, bandwidth limits, and EQ.