🎬 AI 视频工厂 | 填个主题就出片(文案/配音/配图/合成全自动)去体验 →
‹ 返回总目录

nodejs-backend

| 2026-09-05 收录

工具 最近更新09-24
☆ 收藏
🛒 📚 AI提效实战指南 · 图解Skill🛒 📱 大流量手机卡 · 低月租📣 加入推广 · 佣金80-300/张 ›

🛍️ 更多精选好物 ›

392
📦 榜单安装量
707
⭐ GitHub Stars
fork 58
2026-09-24
🗓️ 最近推送
2025-12-26
🌱 项目创建
💻 Python · MIT · 🐛 开放 Issue:0

📝 工具简介

What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center

📖 怎么用

安装可 `git clone https://github.com/alinaqi/maggy.git`,再 `cd maggy && ./install.sh`;或 `pipx install maggy-harness`(也可 `pip install maggy-harness`)。配置/初始化:跑 `maggy bootstrap`,它会装 skills、hooks、~/bin model wrappers、plugins。开始用:跑 `maggy serve`,会从本地 repos 自动配置,然后打开 dashboard。之后直接用自然语言提需求,比如“review the auth middleware for timing attacks”或“push to git”,它会走 intent 匹配、路由和检查流程。先 Bootstrap,需要 harness 再加 Maggy。

📄 README 要点

这个仓库里同时放了 Claude Bootstrap 和 Maggy 两样东西。Claude Bootstrap 是一套可安装的配置包,包含 skills、hooks、rules 和模板,能把 Claude Code 变成一个会自我审查、强制跑测试、还能跨会话记住上下文的工程系统。Maggy 则是可选的本地服务器,加上多模型路由、网页仪表盘、意图驱动协议和插件编排,让你在一个面板里把任务分发给 13 个模型。原文建议先从 Bootstrap 开始,需要这套 harness 时再加 Maggy,并提到有 1100 多个测试、73 个技能、15 个 MCP 工具,每天用在生产代码库里。适合想给 Claude Code 加 TDD 强制、质量门禁和跨上下文记忆的独立工程师,也适合想让团队从单一仪表盘路由 Claude、DeepSeek、Kimi、Gemini、Codex 并做成本感知模型选择的人。

查看英文原文
Claude Bootstrap + Maggy Turn Claude Code into a self reviewing, test enforced engineering system that remembers context across sessions — then route work across 13 models from a single dashboard. Claude Bootstrap is an installable config pack (skills, hooks, rules, templates) for Claude Code. Maggy is the optional local server that adds multi model routing, a web dashboard, intent driven protocols, and plugin orchestration. Both live in this repo. Start with Bootstrap; add Maggy when you need the harness. 1100+ tests. 73 skills. 15 MCP tools. Used daily across production codebases. Who This Is For Solo engineers using Claude Code who want TDD enforcement, quality gates, and memory that survives context compaction — without changing their workflow Teams routing work across Claude, DeepSeek, Kimi, Gemini, and Codex from a single dashboard with cost aware model selection Platform engineers building AI assisted developer tooling who need a reference implementation with intent tracking, protocol execution, and plugin architecture Choose Your Path Claude Bootstrap Maggy Harness What it is Skills, hooks, rules installed into /.claude/ Local FastAPI server + web dashboard Install time 30 seconds 5 minutes (Python 3.11+, API keys) Requires Claude Code (also works with Codex, Kimi, Gemini CLI) Everything in Bootstrap + Python + optional Docker You get TDD enforcement, 73 skills, quality gates, ADR reviews, iCPG, Mnemos memory All of Bootstrap + 13 tier routing, skill protocols, Telos testing, Cortex MCP, plugins, dashboard Bootstrap — 30 second install [安装/使用命令见下方] Your next Claude Code session picks it up automatically. Full Harness — zero config [安装/使用命令见下方] (or from source: cd maggy && ./install.sh && maggy serve ) No API keys required to start — Maggy runs in local mode and, on first launch, discovers your local git repos and opens the dashboard pointed at them. Add GITHUB TOKEN / ANTHROPIC API KEY later only if you want GitHub sync or API model features. See GETTING STA

💬 评论(0)

交流使用体验、避坑建议;违规内容将被删除

💬 意见反馈 / 联系客服

数据来源:skills.sh 榜单 + GitHub 公开数据,非人工实测,仅供参考

浙ICP备2023034286号