Explore
MCP servers and skills: search, filter by where they run, and compare.
agent-implementation-skillnestharus
Local
MCP servers and skills: search, filter by where they run, and compare.
Multi-model agent implementation workflow skill for Claude Code. Orchestrates research, evaluation, design baseline, implementation, RCA, and auditing across AI models.
SkillMIT★ 3Few starsNo key
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
PythonMIT★ 21kNo key
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
SkillMIT★ 77No key
MCP Server Framework and Tool Development library for building custom capabilities into agents.
PythonMIT★ 1.1kNo key
Use cultivar to test your Agent Skills and Docs by running them in sandboxes, and across different agents.
OfficialSkillMIT★ 42No key
CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
PythonMIT★ 14No key
MCP server that enables language models to interact with RDKit through natural language
PythonMIT★ 42No key
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQ
SkillMIT★ 50No key
Live road conditions across 37 US states: map, route planner, toll pricing, and AI assistant - plus an MCP server so any assistant gets incidents, closures, chain controls, cameras, and wildfires.
PythonMIT★ 4Few starsNo key
Forecast what will happen, including outcomes of your decisions.
PythonMIT★ 57Needs a key
Regression testing and evals for LLM applications in CI. A pytest plugin and an MCP server, with the baseline in your repository, not on someone's server.
PythonApache-2.0★ 8No key
Independent CLI benchmark harness for agent-memory backends (MemPalace, Mem0, Zep, OpenViking); publishes raw eval logs.
PythonApache-2.0★ 2Few starsNo key
How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to
SkillMIT★ 13No key
Djævin: calibrated local-first decision layer with a Devin ACP backend - no API key needed
PythonMIT★ 6No key
Persistent, semantic news intelligence layer for AI agents — built on GNews (106k+ monthly PyPI). Python lib + MCP server + Claude Code skill.
PythonMIT★ 8No key
The free, open watchdog for retracted & problematic citations — Retraction Watch + OpenAlex + Crossref, reconciled conservatively. MCP server + web checker, evals-backed.
PythonMITFew starsNo key
Build durable agent harnesses so smaller models can do repeatable, verifiable work — a versioned folder with tools, guardrails, validators, and measured evidence from every run.
SkillApache-2.0★ 4Few starsNo key
Brevet: Change control for what AI agents learn
PythonApache-2.0★ 1Few starsNo key
PythonMIT★ 2Few starsNo key
Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code must keep passing them — zero LLM calls at inference. Try: u
SkillApache-2.0★ 4Few starsNo key
Who stands behind it
