Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
1–5 of 5 tools for “evals”
Clear allOptimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
skill/Apache-2.0/★ 65/no key
CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
skill/MIT/★ 14/no key
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
mcp/link only/★ 4.8k
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
skill/MIT/★ 220/no 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.
skill/Apache-2.0/★ 9/no key
Who stands behind it
Who stands behind it
