a2a-opencode

OpenCode is a production-grade agent runtime that supports Anthropic, OpenAI, GitHub Copilot, and more. It already handles multi-step planning, MCP tool execution, and streaming across any provider you configure.

a2a-opencode exposes it as a standalone, interoperable agent via the A2A protocol. Drop a JSON config file in, get a fully spec-compliant A2A server out. Any orchestrator that speaks A2A can discover and call it — swap the LLM provider in one config line without changing orchestration code.

The pattern: MCP is the vertical rail — how agents access tools. A2A is the horizontal rail — how agents talk to each other. This library adds the horizontal rail to OpenCode, making it vendor-neutral by default.

Features:

Full A2A v0.3.0 protocol — Agent Card, JSON-RPC, REST, SSE streaming
Powered by OpenCode with support for any LLM provider (Anthropic, OpenAI, GitHub Copilot, and more)
MCP tool server support — HTTP, SSE, stdio, and OAuth transports
Multi-turn conversations via persistent OpenCode sessions
SSE event streaming with automatic reconnect and polling fallback
Auto-approval of tool permissions with configurable overrides
JSON config file with layered overrides (JSON → env vars → CLI flags)
Docker-ready with corporate proxy CA support
TypeScript source with full type declarations
Postman collection included for API exploration

Why not just integrate the LLM provider API directly?

Direct provider integrations work — but they create vendor lock-in at the integration layer. Switching from Claude to GPT-4.1 means rewriting SDK calls. Adding a second agent type means a second bespoke integration.

With the A2A protocol surface:

Your orchestrator speaks one interface regardless of which provider is behind it
Switch providers by changing one line in config.json — orchestration stays the same
Run multiple specialized agents (different providers, different system prompts) behind a single protocol interface
Any A2A-compatible system can discover and call your agent via Agent Card

Works with agent frameworks

This library complements — not replaces — frameworks like LangGraph, Google ADK, Microsoft Agent Framework, and CrewAI. Use those frameworks for orchestration, state, and memory control. Use a2a-opencode as the execution node they call.

LangGraph / ADK / Microsoft Agent Framework
        (state, memory, flow control)
                    ↓
              A2A Protocol
                    ↓
             a2a-opencode
      (OpenCode + any LLM provider)

Quick Start

# Install globally
npm install -g a2a-opencode

# Start OpenCode server (required — runs on port 4096 by default)
opencode serve

# In a separate terminal, run the bundled example agent
a2a-opencode --config agents/example/config.json

Or run without installing:

npx a2a-opencode --config agents/example/config.json

Prerequisites: OpenCode installed and running (opencode serve). The wrapper connects to it on http://localhost:4096 by default.

Architecture

A2A Client (Orchestrator / Inspector / curl)
  │
  │  JSON-RPC or REST over HTTP
  ▼
Express Server  (a2a-opencode)
  │  ├─ /.well-known/agent-card.json  → Agent Card
  │  ├─ /a2a/jsonrpc                  → JSON-RPC  (tasks/send, tasks/sendSubscribe, …)
  │  ├─ /a2a/rest                     → REST handler
  │  ├─ /context                      → Read context.md
  │  ├─ /context/build                → Trigger context discovery
  │  └─ /health                       → Health check
  │
  │  @a2a-js/sdk  DefaultRequestHandler
  ▼
OpenCodeExecutor  (AgentExecutor)
  │  ├─ SessionManager      — contextId → OpenCode session
  │  ├─ EventStreamManager  — SSE polling + automatic reconnect
  │  ├─ PermissionHandler   — auto-approves tool calls
  │  └─ EventPublisher      — OpenCode events → A2A events
  │
  │  @opencode-ai/sdk  (HTTP + SSE)
  ▼
OpenCode Server  (opencode serve)
  │  ├─ LLM inference  (Anthropic, OpenAI, GitHub Copilot, …)
  │  └─ MCP tool execution
  │
  │  MCP Protocol  (HTTP / SSE / stdio / OAuth)
  ▼
MCP Servers  (filesystem, custom tools, …)

Installation

# npm
npm install a2a-opencode

# yarn
yarn add a2a-opencode

# pnpm
pnpm add a2a-opencode

Usage

CLI

a2a-opencode --config agents/example/config.json

Full flag reference:

a2a-opencode [options]

  --config, --agent-json <path>   JSON agent config file
  --port <number>                 Server port                      (default: 3000)
  --hostname <addr>               Bind address                     (default: 0.0.0.0)
  --advertise-host <host>         Hostname for agent card URLs     (default: localhost)
  --opencode-url <url>            OpenCode server URL              (default: http://localhost:4096)
  --model <provider/model>        LLM model                        (default: provider default)
                                  e.g. anthropic/claude-sonnet-4-20250514
  --agent <name>                  OpenCode agent preset
  --directory <path>              Project directory for OpenCode
  --agent-name <name>             Agent display name
  --agent-description <desc>      Agent description
  --auto-approve                  Auto-approve all tool permissions (default: on)
  --no-auto-approve               Require manual permission approval
  --auto-answer                   Auto-answer questions            (default: on)
  --no-auto-answer                Do not auto-answer questions
  --stream-artifacts              Stream chunks in real time (A2A spec mode)
  --no-stream-artifacts           Buffer artifacts — Inspector-compatible (default)
  --log-level <level>             debug | info | warn | error      (default: info)
  --help                          Show this help
  --version                       Show version

Programmatic API

import { createA2AServer, resolveConfig } from 'a2a-opencode';

const config = await resolveConfig({ configPath: 'agents/example/config.json' });
const { server, url } = await createA2AServer(config);

console.log(`Agent running at ${url}`);

Configuration

Config is resolved in priority order: defaults ← JSON file ← env vars ← CLI flags

JSON Config File

Create a config.json (see agents/example/config.json for the fully annotated template):

{
  "agentCard": {
    "name": "My Agent",
    "description": "What my agent does",
    "version": "1.0.0",
    "protocolVersion": "0.3.0",
    "streaming": true,
    "skills": [
      {
        "id": "my-skill",
        "name": "My Skill",
        "description": "Describe the skill",
        "tags": ["example"]
      }
    ]
  },
  "server": {
    "port": 3000,
    "hostname": "0.0.0.0",
    "advertiseHost": "localhost"
  },
  "opencode": {
    "baseUrl": "http://localhost:4096",
    "model": "anthropic/claude-sonnet-4-20250514",
    "systemPrompt": "You are a specialist agent that...",
    "contextFile": "context.md",
    "autoApprove": true,
    "autoAnswer": true
  },
  "mcp": {
    "my-tools": {
      "type": "http",
      "url": "http://localhost:8002/mcp"
    }
  }
}

Environment Variables

Variable	Description	Default
`PORT`	Server port	`3000`
`HOSTNAME`	Bind address	`0.0.0.0`
`ADVERTISE_HOST`	Hostname in agent card URLs	`localhost`
`OPENCODE_URL`	OpenCode server URL	`http://localhost:4096`
`OPENCODE_MODEL`	LLM model (`provider/model`)	(OpenCode default)
`WORKSPACE_DIR`	Project directory for OpenCode	(empty)
`AUTO_APPROVE`	Auto-approve tool permissions	`true`
`AUTO_ANSWER`	Auto-answer questions	`true`
`STREAM_ARTIFACTS`	Stream chunks in real time	`false`
`LOG_LEVEL`	`debug`\|`info`\|`warn`\|`error`	`info`
`AGENT_NAME`	Override agent card name	(from config)
`AGENT_DESCRIPTION`	Override agent card description	(from config)

See .env.example for the full reference.

Bundled Agent Examples

Example Agent (minimal)

./agents/example/start.sh start
./agents/example/start.sh status
./agents/example/start.sh logs
./agents/example/start.sh stop
./agents/example/start.sh foreground   # useful for debugging

Runs on port 3000. No external tools. Good starting point for custom agents.

The start.sh script manages both the OpenCode subprocess and the A2A wrapper.

Creating Your Own Agent

# Copy the example agent
cp -r agents/example agents/my-agent

# Edit the config
$EDITOR agents/my-agent/config.json

# Start it
./agents/my-agent/start.sh start

MCP Tool Servers

HTTP / SSE server

"mcp": {
  "my-tools": {
    "type": "http",
    "url": "http://localhost:8002/mcp"
  }
}

stdio server (child process)

"mcp": {
  "filesystem": {
    "type": "stdio",
    "command": "npx",
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/workspace"]
  }
}

OAuth server

"mcp": {
  "my-oauth-tools": {
    "type": "oauth",
    "url": "https://api.example.com/mcp",
    "clientId": "...",
    "clientSecret": "..."
  }
}

Docker

# Build
docker build -t a2a-opencode:latest .

# Run (OpenCode must be accessible from within the container)
docker run -p 3000:3000 \
  a2a-opencode:latest --config agents/example/config.json

# Mount a custom agent config
docker run -p 3000:3000 \
  -v /host/path/my-agent:/app/agents/my-agent \
  a2a-opencode:latest --config agents/my-agent/config.json

Corporate Proxy (Netskope / Zscaler)

Mount your CA certificate into the container and the entrypoint injects it automatically:

docker run -p 3000:3000 \
  -v /path/to/corporate-ca.crt:/etc/ssl/certs/corporate-ca.crt:ro \
  a2a-opencode:latest --config agents/example/config.json

A2A Protocol

Implements A2A v0.3.0:

Endpoint	Description
`GET /.well-known/agent-card.json`	Agent identity and capabilities
`POST /a2a/jsonrpc`	JSON-RPC: `tasks/send`, `tasks/sendSubscribe`, `tasks/get`, `tasks/cancel`
`POST /a2a/rest`	REST equivalent
`GET /health`	Health check
`POST /context/build`	Trigger context discovery
`GET /context`	Read the built context file

Streaming uses SSE for real-time status updates and artifact chunks. Set --stream-artifacts for spec-correct chunk streaming or leave it unset (default) for buffered output compatible with the A2A Inspector.

API Reference (Postman)

A full Postman collection covering all endpoints is included at docs/A2A-OpenCode-Wrapper.postman_collection.json. Import it into Postman and set the baseUrl variable to your running agent's URL.

Context Building

# Trigger the LLM to discover available data and write context.md
curl -X POST http://localhost:3000/context/build

# Read the built context
curl http://localhost:3000/context

Contributing

Contributions are welcome! Please read CONTRIBUTING.md first.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
.github		.github
agents/example		agents/example
docs		docs
src		src
.env.example		.env.example
.gitignore		.gitignore
CHANGELOG.md		CHANGELOG.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
Dockerfile		Dockerfile
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
entrypoint.sh		entrypoint.sh
package-lock.json		package-lock.json
package.json		package.json
server.sh		server.sh
tsconfig.json		tsconfig.json

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

a2a-opencode

Why not just integrate the LLM provider API directly?

Works with agent frameworks

Quick Start

Architecture

Installation

Usage

CLI

Programmatic API

Configuration

JSON Config File

Environment Variables

Bundled Agent Examples

Example Agent (minimal)

Creating Your Own Agent

MCP Tool Servers

HTTP / SSE server

stdio server (child process)

OAuth server

Docker

Corporate Proxy (Netskope / Zscaler)

A2A Protocol

API Reference (Postman)

Context Building

Contributing

License

About

Uh oh!

Releases 2

Packages

Uh oh!

Contributors

Uh oh!

Languages

License

shashikanth-gs/a2a-opencode

Folders and files

Latest commit

History

Repository files navigation

a2a-opencode

Why not just integrate the LLM provider API directly?

Works with agent frameworks

Quick Start

Architecture

Installation

Usage

CLI

Programmatic API

Configuration

JSON Config File

Environment Variables

Bundled Agent Examples

Example Agent (minimal)

Creating Your Own Agent

MCP Tool Servers

HTTP / SSE server

stdio server (child process)

OAuth server

Docker

Corporate Proxy (Netskope / Zscaler)

A2A Protocol

API Reference (Postman)

Context Building

Contributing

License

About

Resources

License

Code of conduct

Contributing

Security policy

Uh oh!

Stars

Watchers

Forks

Releases 2

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages