Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
High-Performance Knowledge Graph MCP Server (Haskell + C++ Supervisor)
SkillMITFew starsNo key
High-concurrency API rate limiter implementing sliding-window log calculations and exponential backoff retry headers
SkillLink only★ 7
High-concurrency API rate limiter implementing sliding-window log calculations and exponential backoff retry headers
SkillLink only★ 7
Voice-first restaurant MCP server (Rust, Streamable HTTP, MCP 2025-11-25): allergen-aware menu search, table negotiation and holds, pickup orders, opt-in memory with forget-me, and simulated deposits
SkillMIT★ 1Few starsNo key
DUME Studio. A Persistent Memory MCP and Database
PythonMIT★ 2Few starsNo key
High-performance native Rust Model Context Protocol (MCP) server for CodeAtlas — AST code intelligence, codebase knowledge graphs, semantic memory, and AI agent orchestration.
Node.jsMITFew starsNo key
🔎High-assurance static invariant, causation and concurrency diagnostic engine for Python
PythonMIT★ 1Few starsNo key
Claude Code plugin and MCP server: a cheap model, DeepSeek V4.1 Flash, reviews Claude's code for bugs and gives second opinions for under a cent each. Claude stays the sheriff.
PythonMIT★ 2Few starsNeeds a key
Zero-dependency Universal AI Gateway & Smart Router for Node.js/Edge - Circuit Breakers, Semantic Cache, MCP Tool Loop, Reversible PII Vault & 9+ Providers (OpenAI, Claude, Gemini, DeepSeek, Groq, Oll
SkillMIT★ 4Few starsNo key
Diff AGENTS.md, CLAUDE.md, Cursor rules and MCP server configs between git refs; flag new MCP servers, widened permissions, removed guardrails and hidden Unicode. TypeScript CLI + GitHub Action.
Node.jsMITFew starsNo key
🦅🪽 Sovereign Self-Evolving AI Agent Framework: Hermes closed-loop skill evolution x OpenClaw <1.5K token frugality x Gemini Agent Booster (O(1) Thinking Budget & 90% KV-Cache) x Zero-Trust VM Sandbo
SkillMIT★ 1Few starsNo key
Transform LinkedIn saved posts into an interactive, interconnected Obsidian knowledge graph. Features a zero-config web dashboard, hybrid LLM routing (Groq + local vLLM/llama.cpp), vector embeddings,
PythonMITFew starsNo key
Open reference architecture for agentic built-environment intelligence, coupling Model Context Protocol (MCP), ReAct multi-agent reasoning, deterministic statutory compliance, and Rust Monte Carlo ris
SkillApache-2.0Few starsNo key
Delegate coding work from Claude Code to a team of Google Antigravity (agy) specialists. MCP server, web panel, token usage tracking, verification gate and safe process control.
Node.jsMITFew starsNo key
Traceable issue-driven Codex workflow with codebase-memory-mcp, OpenCodeReview, GitHub Issues, PRs, and CI.
SkillMIT★ 1Few starsNo key
Deterministic static security review for AI agent skills and MCP configs — 22 rules, zero-dependency core, SARIF for CI.
PythonMITFew starsNo key
Is your AI agent setup safe? One command scans your MCP servers (Claude, Cursor, VS Code, Windsurf) for security risks.
Node.jsMIT★ 1Few starsNo key
🌍 The Global Standard for Respectful AI Communication & High-Signal Prompting (RAHSPS). Stop feeding garbage to LLMs. Includes llms.txt, universal agent rules (Cursor, Claude Code, Gemini, Windsurf,
PythonMIT★ 1Few starsNo key
Portable control plane for skills, plugins, MCP servers, and policy across coding agents — with drift detection and a local personal overlay.
Node.jsApache-2.0Few starsNo key
Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server
SkillMIT★ 2Few starsNo key
OpenClaw GenPark Curator - High-throughput MinHash LSH dataset deduplication and content quality scoring engine.
SkillMIT★ 7No key
OpenClaw GenPark Sentiment Harvester - High-throughput lexicon-decay sentiment polarity engine with valence shifting and time-weighted stream aggregation.
SkillMIT★ 7No key
Layer-aware Dockerfile audit — 32 deterministic rules, zero dependencies, SARIF for CI, MCP server
PythonMITFew starsNo key
Local long-term memory for AI agents. Keeps every conversation word for word, costs nothing to save, and is shared by all your agents. 88.8% on LongMemEval.
PythonApache-2.0★ 9No key
Who stands behind it