reference implementation

Reference implementation for building and understanding AI evaluation systems, including rule-based evaluation, human review, LLM-as-a-Judge, online evaluation, and experiment comparison for a flight search app.

An open agent-identity protocol with a shipped reference implementation, TypeScript SDK, conformance test vectors, and protocol docs for identity, discovery, payments, and audit flows.

A governed workflow execution spec for MCP hosts, with fail-closed semantics, version pinning, checkpoint enforcement, and a reference implementation plus conformance suite.