Agent2Agent (A2A) – AgentCards, Servers, Clients, Docs

Elkar - Task management for AI Agents, ready for Agent2Agent (A2A) protocol

Only natural-language is enough for you & your team.

Mock HTTP/SSE and LLM servers, inspired by wiremock, but with response streaming and SSE

A JS/TS SDK for the Agent2Agent Protocol

A Java implementation of the A2A protocol, that's agent to agent scenarios with google a2a protocol

AgentX python SDK. Build multi-agent AI workforce.

Cognisphere ADK is an AI agent development framework built on Google's Agent Development Kit (ADK)

Instead of dumping 1000+ tools into a model’s prompt and expecting it to choose wisely, the Unified MCP Tool Graph equips your LLM with structure, clarity, and relevance. It fixes tool confusion, prevents infinite loops, and enables modular, intelligent agent workflows.

A2A-4J is a Java implementation of the Agent-to-Agent (A2A) protocol. The A2A protocol facilitates standardized communication between AI agents, enabling them to exchange tasks, messages, and artifacts.

it built itself

kbs_agent_a2a 智能体协议适配中间件

Open-source gateway and community to make AI agents interoperable using Google's A2A protocol – like Hugging Face, but for agents.

An agent playground (without authentication) in a single repo for fastest turn around cycles during experiments.

A2A-MCP official website with modern UI and dark mode support

AG2A: AutoGen Agent-to-Agent - A library for AutoGen (AG2) agents with MCP capabilities exposed as A2A agents

A2A ⚡ MCP Agent

a2a‑go is a reference Go implementation of the Agent‑to‑Agent (A2A) protocol by Google, including the proposed interoperability with the Model Context Protocol (MCP) from Anthropic.

Jira A2A Proof of Concept

Discover, compare, and implement the best agent-to-agent protocols for your AI systems. Enable your AI agents to communicate effectively with our curated protocol directory.