MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Chaos testing for AI agents. Break the MCP tools your agent depends on, score how it copes, fix what broke. Claude Code plugin + GitHub Action.
GoMITFew starsNo key
Chaos engineering for MCP agents: a stdio proxy that injects timeouts, errors, malformed JSON, schema drift and stale results, plus a benchmark that measures how agents recover.
PythonMITFew starsNo key
An open protocol for the matters a person holds, shared by every AI assistant they use: specification, conformance tests and a reference MCP server.
Node.jsApache-2.0Few starsNo key
Local-first context, memory and state layer for AI coding agents (engine only; data stays private)
SkillMITFew starsNo key
Universal Knowledge Base & Zero-Leak Security Hub for AI Agents (Antigravity, Claude Code, Windsurf, Cursor, Cline, Roo Code, DeepSeek, OpenCode)
Node.jsMIT★ 3Few starsNo key
The Universal Behavioral Contract & Context Engine that turns any AI coding agent into a disciplined senior engineer — eliminating regressions, hallucinations, and unwanted pushes.
Node.jsMIT★ 1Few starsNo key
Free animated course on agentic engineering: building real software with AI coding agents (Claude Code, Codex, Cursor). 24 lessons from 126 talks & articles. Your agent can take it too: npx skills add
MCPLink only★ 1Few stars
A practical roadmap for senior software engineers transitioning into AI engineering. Covers LLMs, context engineering, RAG, MCP, agentic AI, security, guardrails, evals, observability, LLMOps, AI syst
SkillMIT★ 1Few starsNo key
Shared memory, focused engineering practices and reliable handoffs for coding agents. Give your agent one setup prompt.
SkillMIT★ 5No key
A 36-chapter curriculum on building, evaluating, securing and operating LLM agents in production: patterns, context engineering, memory, frameworks, MCP and A2A, evals, observability, security, and FD
MCPLink only★ 1Few stars
复杂生产环境 AI 工程化落地全链路知识库：理论底座归一化 + Python/Java 双栈生产实践（RAG·Agent·MCP·A2A·Agentic-RL·评估），含 67 个可运行代码范式与计算机基础支撑。
MCPLink onlyFew stars
Zero-G Reverse Engineering Anything & Verified Safe Rust Reconstruction for Gemini 4 Argon + Google Antigravity 2.0 (4-Mount Recon Kits, Whole-Subgraph Extraction, 10,000-Vector Differential Parity Re
Node.jsMIT★ 11No key
AgentEng: Agent Engineering HQ - CLI, MCP, A2A and Agent Engineering for AgentEng HQ events
PythonApache-2.0Few starsNo key
Charter packs, served over MCP: the runtime behind R28's MCP servers. The SDK is r28ai/charter.
PythonApache-2.0Few starsNo key
Unofficial, auto-updating agent skill that distills Anthropic's claude.dev engineering blog into own-words playbooks for Claude Code and Codex. Not affiliated with Anthropic.
SkillMIT★ 4Few starsNo key
Marcelo Miyake’s GitHub profile — software architecture, distributed systems, mission-critical software, and AI engineering.
MCPLink onlyFew stars
An extensible collection of AI agent skills for software documentation, architecture analysis, reverse engineering, AI integration planning, technical knowledge management, and presentation generation
SkillApache-2.0★ 1Few starsNo key
Agent skill to reverse engineer a SaaS product through the browser into a knowledge base for rebuilding it: screens, rules, data model, design tokens and production barriers, without touching producti
SkillMIT★ 151No key
AI coding skill that actually works. Structured 6-doc context system prevents hallucinations, maintains consistency across sessions. Quality frameworks for accessibility, security, SEO, performance, l
SkillMIT★ 3Few starsNo key
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the
PythonMIT★ 1.0kNo key
🚀 Enterprise Multi-Agent Operating Framework: 404 curated production skills & 120 specialized subagents for Antigravity, Claude, and Codex with 70% token compression.
SkillMIT★ 2Few starsNo key
Hands-on playbook for REA: minimal Electron target, Evidence extractor with file:line refs, MCP probe, and a verified Decompile -> Understand -> Recreate loop. No reverse-engineering engine required.
Node.jsMIT★ 1Few starsNo key
High-performance multi-engine game asset extractor, native container parser (Godot, Unreal, Unity, Windows PE), and AI reverse engineering orchestrator with MCP support
Node.jsMITFew starsNo key
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
PythonMIT★ 236No key
Who stands behind it
