MCP servers and skills: search, filter by where they run, and compare.
Author verifiable eval records through a draft → review → revise → submit loop with server-enforced graders; compile to JSONL/CSV/Inspect/lm-eval via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 1Few starsNo key
A Node.js package and GitHub Action for evaluating MCP (Model Context Protocol) tool implementations using LLM-based scoring. This helps ensure your MCP server's tools are working correctly and perfor
Node.jsMIT★ 134No key
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it
OfficialSkillMIT★ 1.3k in collectionNo key
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv',
OfficialSkillApache-2.0★ 3.6k in collectionNo key
MCP Server Framework and Tool Development library for building custom capabilities into agents.
PythonMIT★ 1.1kNo key
Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
Node.jsMIT★ 4Few starsNo key
242 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical, social science, Turkish academia & more. Every skill ships a
SkillMIT★ 76No 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
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
SkillApache-2.0★ 65No key
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
SkillMIT★ 223No key
SQL editor/viewer for SQLite and PostgreSQL. Features an interactive Schema Visualizer, Context-Aware AI (Text-to-SQL), and transactional batch operations. Built with Electron and React.
Node.jsMIT★ 7No key
The memory layer for production AI agents. Python + JS SDKs, 24 framework integrations, MCP server.
Hosted by authorApache-2.0★ 77No key
Ship a remote MCP connector that passes Claude directory review on the first try. Next.js + mcp-handler template, SSRF-safe fetch, rate limits for Claude's egress range, evals, policy pages, submissio
Hosted by authorMITFew starsNo key
Independent CLI benchmark harness for agent-memory backends (MemPalace, Mem0, Zep, OpenViking); publishes raw eval logs.
PythonApache-2.0★ 2Few starsNo key
Agent skill and reference runtime for maintaining a git-backed business ontology: source intake, review gates, evals, and MCP/GBrain boundaries.
SkillMIT★ 3Few starsNo key
A source-grounded Ryan perspective skill for relationship, boundaries, self-awareness, and authentic expression.
SkillMIT★ 3Few starsNo key
Djævin: calibrated local-first decision layer with a Devin ACP backend - no API key needed
PythonMIT★ 6No key
Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.
Node.jsApache-2.0★ 8No key
Token-efficient code reading for AI coding agents: budgeted, symbol-aware, diff-aware reads over MCP.
SkillMIT★ 1Few starsNo 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
Fleet Pi , workspace for Pi-powered coding agents, with durable plans, memory, and repo-scoped tools
SkillApache-2.0★ 6No key
Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured
SkillMIT★ 11No key
Let your coding agent fix a prompt until it actually works, and prove it did. A self-hosted MCP server: cross-vendor judges, frozen baselines and memory.
SkillApache-2.0★ 9No key
Who stands behind it
