An agentic evaluation harness for MCP servers — can an AI agent actually accomplish real tasks with this server's tools?
Terminal-based AI agent — a function-calling loop with minimum harness
Memory you can verify — a trust layer between an AI coding agent and its own past: per-hit staleness verdicts, claim-level use attribution, measured effectiveness, episodic run-state. MCP-native, local-first, MIT, no cloud.
graph8 MCP server - GTM operations for AI agents
MCP server for swafra — Leiden-chunked, graph-linked semantic memory for Claude AI and ChatGPT
