Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.
Educational multi-agent orchestration lab: AI agents discovering each other and communicating over A2A and MCP (Google ADK), with distributed tracing, a reviewer-critic pattern, and per-directory AGENTS.md docs
This project is a technical talk demonstration showcasing A2A (Agent-to-Agent) communication connecting multiple distinct AI agent frameworks and MCP servers together under a unified orchestration layer.
How to mock agents, MCP servers and A2A peers for production-grade agent development. Protocol surfaces verified against MCP 2026-07-28 and A2A v1.0 (August 2026).