Skip to content

AgentMesh Server

Turn AI Agents Into Production Systems.

AgentMesh Server is a production-ready implementation of the A2A (Agent-to-Agent) Protocol, the open standard from the Linux Foundation that enables AI agents to communicate, collaborate, and solve complex problems together.

  • Get Started in 5 Minutes

    Install AgentMesh and run your first multi-agent workflow

    Quick Start

  • Full A2A Protocol Support

    Complete implementation of the A2A specification with extensions

    A2A Protocol

  • Deploy Anywhere

    Docker, Kubernetes, or bare metal with Helm charts included

    Deployment

  • OpenCode Integration

    Bridge AI coding agents to your codebase with session management

    OpenCode

What is AgentMesh?

AgentMesh Server provides the infrastructure layer for running AI agents in production:

  • A2A Protocol Native — Full implementation of the A2A specification for agent-to-agent communication
  • Distributed Workers — Run agents across multiple machines with automatic task routing
  • Real-time Streaming — SSE-based live output streaming for long-running agent tasks
  • Session Management — Resume conversations, sync across devices, maintain context
  • Enterprise Security — Keycloak OIDC, API tokens, audit logging
  • OpenCode Bridge — Native integration with OpenCode AI coding agents

A2A Protocol Implementation

AgentMesh implements the complete A2A Protocol specification:

A2A Feature AgentMesh Support Reference
Agent Discovery ✅ /.well-known/agent-card.json Spec §5
JSON-RPC 2.0 ✅ Full support Spec §6
Task Management ✅ Create, cancel, status Spec §7
Streaming (SSE) ✅ Real-time artifacts Spec §8
Push Notifications ✅ Webhook callbacks Topics
Multi-turn Conversations ✅ Session continuity Topics

Plus AgentMesh extensions:

  • Distributed Task Queue — Redis-backed task distribution across workers
  • OpenCode Integration — AI coding agent bridge with codebase registration
  • Monitor UI — Web dashboard for real-time agent observation
  • MCP Tools — Model Context Protocol tool server

Quick Example

# Install
pip install a2a-server-mcp

# Run server
agentmesh serve --port 8000

# In another terminal, send a task
curl -X POST http://localhost:8000/v1/a2a \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tasks/send",
    "params": {
      "message": {
        "role": "user",
        "parts": [{"text": "Analyze this codebase"}]
      }
    },
    "id": "1"
  }'

Architecture Overview

graph TB
    subgraph Clients
        UI[Web Dashboard]
        CLI[CLI / SDK]
        Agent[External Agents]
    end

    subgraph AgentMesh Server
        API[FastAPI Server]
        A2A[A2A Protocol Handler]
        MCP[MCP Tool Server]
        Monitor[Monitor API]
    end

    subgraph Infrastructure
        Redis[(Redis Broker)]
        DB[(SQLite/Postgres)]
        Keycloak[Keycloak Auth]
    end

    subgraph Workers
        W1[Worker 1]
        W2[Worker 2]
        OC[OpenCode Bridge]
    end

    UI --> API
    CLI --> API
    Agent --> A2A

    API --> A2A
    API --> MCP
    API --> Monitor

    A2A --> Redis
    Monitor --> DB
    API --> Keycloak

    Redis --> W1
    Redis --> W2
    Redis --> OC

Next Steps