5-agent AI system using CrewAI, MCP, and A2A Protocol to autonomously generate API test suites from OpenAPI specs — GPT-4o/Claude Sonnet via LiteLLM with LangSmith tracing
An educational demonstration of Google's Agent-to-Agent (A2A) protocol v1 through a multi-agent storytelling system. Three AI agents collaborate iteratively to adapt and enhance stories, showcasing real-world A2A communication patterns.
A comprehensive Apache Camel component for Agent-to-Agent (A2A) communication using JSON-RPC 2.0 over WebSocket connections. This component enables seamless integration between AI agents, microservices, and distributed systems through standardized message passing.
MPCP — an open, transport-agnostic protocol for governed, auditable coordination among mixed parties: humans and AI agents as first-class, symmetric participants (P2P/P2A/A2A). Sits above MCP/A2A.