Open platform for AI agent networks — semantic discovery, a secure broker, and multidirectional agent-to-agent communication with Google A2A protocol support. Async Python (FastAPI), Postgres, Qdrant, Redis.

End-to-end encrypted communication for AI agents. The security layer that Google A2A forgot.

A2A protocol enables agent communication. AXME adds durable lifecycle, retries, timeouts, and human checkpoints.

A collection of Google A2A agents and clients, deployed on Cloud Run or Railway.

A hands-on tutorial implementation of Google's Agent2Agent (A2A) protocol. Three multi-agent travel planners Flight, Hotel, and Itinerary collaborate via Agent Cards, SSE streaming, and artifact passing. Includes LangGraph and CrewAI integrations.

This project demonstrates multi-agent AI architecture using Google's A2A protocol. ResearchAgent searches arXiv papers & delegates summarization to SummarizerAgent via Agent Cards & Tasks, showcasing distributed agent collaboration beyond monolithic LLM calls.

Exploring Google’s A2A AI System: Agent-to-Agent Workflows, Routing, and Conversation History

MCP server for agent-to-agent communication — capability discovery, task delegation, and result aggregation across MCP agents

AgentCard — standardized identity & capability schema for AI agents. Rust reference implementation: github.com/kwailapt/aevum/tree/main/crates/agent-card

Enterprise-grade TypeScript implementation of Google's Agent-to-Agent (A2A) protocol with a bidirectional A2A ↔ MCP bridge, OAuth2/JWT auth, Redis/Postgres persistence, SSE streaming, and OpenTelemetry observability.

A .NET library that enables ASP.NET Application to host Agent2Agent Server following Google's A2A protocol

Cross-device Agent-to-Agent communication bridge for OpenClaw, powered by Google A2A Protocol

Agent-to-Agent Protocol Specification — agent:// URI scheme for AI agent identity and discovery