🔓AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用
// skillsNarratorAI-Studio/★ 1,439◷ MIT[ claude ]
Healthiest
// sorted by health — what's thriving right now
// observatory (1918)
🔓
🔓Lightweight coding agent written in Rust, optimized for memory footprint and performance
// devtoolsgi-dellav/⟨Rust⟩★ 1,433◷ GPL-3.0[ claude ]
🔓OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool call…
// ragwaybarrios/⟨Python⟩★ 1,411◷ Apache-2.0[ claude ]
🔓Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and…
// automationPriivacy-ai/⟨Python⟩★ 1,400◷ MIT[ claude ]
🔓Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.
// automationyohey-w/⟨Shell⟩★ 1,391◷ MIT[ claude ]
🔓Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
// datatheopenco/⟨TypeScript⟩★ 1,378◷ NOASSERTION[ claude ]
🔓Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gem…
// devtoolsm0n0x41d/⟨Go⟩★ 1,360◷ NOASSERTION[ claude ]
🔓Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.
// mcp-serversjustrach/⟨Zig⟩★ 1,341◷ BSD-3-Clause[ claude ]
🔓Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized for Google rankings and AI citations. Active deve…
// contentAgriciDaniel/⟨Python⟩★ 1,277◷ MIT[ claude ]
🔓⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u.a.) – inzwischen verbessert und im A…
// skillsKlotzkette/⟨Python⟩★ 1,263◷ Apache-2.0[ claude ]
🔓Natural voice conversations with Claude Code
// mcp-serversmbailey/⟨Python⟩★ 1,255◷ MIT[ claude ]
🔓Production-ready AI chat. Start here and make it your own. Formerly Sparka AI
// dataFranciscoMoretti/⟨TypeScript⟩★ 1,180◷ NOASSERTION[ claude ]
🔓Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.
// otherbrainlid/⟨Elixir⟩★ 1,177◷ NOASSERTION[ claude ]
🔓180 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes — one source, every AI tool
// skillsmohitagw15856/⟨JavaScript⟩★ 1,165◷ MIT[ claude ]
🔓The memory-first self-improving agent harness built on EverOS.
// automationEverMind-AI/⟨Python⟩★ 1,160◷ Apache-2.0[ claude ]
🔓Chat app for Android that supports answers from multiple LLMs at once. Bring your own API key AI client. Supports OpenAI, Anthropic, Google, and Ollama. Desi…
// devopsTaewan-P/⟨Kotlin⟩★ 1,158◷ GPL-3.0[ claude ]
🔓Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
// automationthClaws/⟨Rust⟩★ 1,142◷ Apache-2.0[ claude ]
🔓An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps. I mainly use it as an xcodebuild wrappe…
// skillsconorluddy/⟨Python⟩★ 1,131◷ MIT[ claude ]
🔓SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language projects, 4-language docs. Go CLI, zero…
// devtoolsmodu-ai/⟨Go⟩★ 1,117◷ Apache-2.0[ claude ]
🔓A set of tools that gives agents powerful capabilities.
// automationstrands-agents/⟨Python⟩★ 1,116◷ Apache-2.0[ claude ]
🔓AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for…
// automationDeepMyst/⟨TypeScript⟩★ 1,100◷ Apache-2.0[ claude ]
🔓🦭跨端交接、越用越懂你的桌面 AI 助手——也能服务化常驻、跑在云上 | Desktop AI that hands off across your devices and gets to know you better — also runs headless on a NAS or in the cloud
// automationshiwenwen/⟨Rust⟩★ 1,098◷ MIT[ claude ]
🔓Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS scoring, CISA KEV, MITRE ATT&CK, Shodan, VirusTota…
// mcp-serversmukul975/⟨Python⟩★ 1,064◷ Apache-2.0[ claude ]
🔓The coding agent that answers to you, your model, your machine, your rules.
// mcp-serversGitlawb/⟨Go⟩★ 1,024◷ MIT[ claude ]
🔓Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents…
// automationwithkynam/⟨JavaScript⟩★ 1,015◷ MIT[ claude ]
🔓Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.
// devtoolsasklokesh/⟨Shell⟩★ 1,005◷ NOASSERTION[ claude ]
🔓AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability…
// ragENTERPILOT/⟨Go⟩★ 985◷ MIT[ claude ]
🔓CLI, SDK, and IDE plugins for Duel Agents
// devtools2aronS/⟨TypeScript⟩★ 980◷ MIT[ claude ]
🔓Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, and unlimited context — all on Pyda…
// automationvstorm-co/⟨Python⟩★ 952◷ MIT[ claude ]
🔓AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, an…
// mcp-serversaffaan-m/⟨TypeScript⟩★ 951◷ MIT[ claude ]