> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.

# A2A Protocol

> Agent-to-Agent (A2A) protocol support — expose your agents as A2A servers and call remote A2A agents.

# A2A Protocol

Agentium provides full support for the [Agent-to-Agent (A2A)](https://google.github.io/A2A/) protocol, enabling interoperability between AI agents built on different frameworks.

<Info>
  A2A is an open standard by Google that defines how AI agents communicate with each other via JSON-RPC 2.0 over HTTP. It includes agent discovery, task management, and streaming.
</Info>

***

## Capabilities

Agentium supports both sides of A2A:

<CardGroup cols={2}>
  <Card title="A2A Server" icon="server" href="/a2a/server">
    Expose your Agentium agents as A2A-compliant endpoints. Other frameworks (LangGraph, CrewAI, etc.) can discover and call your agents.
  </Card>

  <Card title="A2A Client" icon="satellite-dish" href="/a2a/client">
    Connect to remote A2A agents. Use them as tools, team members, or call them directly.
  </Card>
</CardGroup>

***

## How It Works

```
┌──────────────────┐         ┌──────────────────┐
│  Agentium Agent    │  A2A    │  Remote Agent     │
│  (Server)         │◄───────►│  (Any Framework)  │
│                   │ HTTP/   │                   │
│  /.well-known/    │  SSE    │  /.well-known/    │
│   agent.json      │         │   agent.json      │
└──────────────────┘         └──────────────────┘
```

1. **Discovery** — Agents publish an Agent Card at `/.well-known/agent.json` describing their capabilities
2. **Communication** — JSON-RPC 2.0 messages over HTTP (`message/send`) or SSE (`message/stream`)
3. **Task Management** — Each interaction creates a task with lifecycle states (submitted → working → completed)

***

## Quick Example

### Expose an agent as A2A server

```typescript theme={null}
import express from "express";
import { Agent, openai } from "@agentium/core";
import { createA2AServer } from "@agentium/transport";

const app = express();

const agent = new Agent({
  name: "assistant",
  model: openai("gpt-4o"),
  instructions: "You are a helpful assistant.",
});

createA2AServer(app, {
  agents: { assistant: agent },
  provider: { organization: "MyCompany" },
});

app.listen(3001);
// Agent Card: http://localhost:3001/.well-known/agent.json
```

### Call a remote A2A agent

```typescript theme={null}
import { A2ARemoteAgent } from "@agentium/core";

const remote = new A2ARemoteAgent({
  url: "http://localhost:3001",
});

await remote.discover();
const result = await remote.run("Hello!");
console.log(result.text);
```