Control Claude Code, Goose, Aider, and Codex with an HTTP API.

You can use AgentAPI:

• to build a unified chat interface for coding agents
• as a backend in an MCP server that lets one agent control another coding agent
• to create a tool that submits pull request reviews to an agent
• and much more!

1. Install agentapi by either:

   • Downloading the latest release binary from the releases page
   • Or building from source:

     go install github.com/coder/agentapi@latest

2. Verify the installation:

   On macOS, if you’re prompted that the system was unable to verify the binary, go to System Settings -> Privacy & Security, click “Open Anyway”, and run the command again.

3. Run a Claude Code server (assumes claude is installed on your system and in the PATH):

   agentapi server -- claude

   If you’re getting an error that claude is not in the PATH but you can run it from your shell, try which claude to get the full path and use that instead.

4. Send a message to the agent:

   curl -X POST localhost:3284/message 
     -H "Content-Type: application/json" 
     -d '{"content": "Hello, agent!", "type": "user"}'

5. Get the conversation history:

   curl localhost:3284/messages

6. Try the demo web chat interface at https://coder.github.io/agentapi/chat. Even though it’s hosted on GitHub Pages, the chat will connect to your AgentAPI server running on localhost:3284.

   If you’re having trouble connecting to the demo chat on Safari, it’s likely because it’s blocking an HTTP-only connection to localhost. The demo may work in a different browser.

Run an HTTP server that lets you control an agent. If you’d like to start an agent with additional arguments, pass the full agent command after the -- flag.

agentapi server -- claude --allowedTools "Bash(git*) Edit Replace"

You may also use agentapi to run the Aider and Goose agents:

agentapi server -- aider --model sonnet --api-key anthropic=sk-ant-apio3-XXX
agentapi server -- goose

An OpenAPI schema is available in openapi.json.

By default, the server runs on port 3284. Additionally, the server exposes the same OpenAPI schema at http://localhost:3284/openapi.json and the available endpoints in a documentation UI at http://localhost:3284/docs.

There are 4 endpoints:

• GET /messages – returns a list of all messages in the conversation with the agent
• POST /message – sends a message to the agent. When a 200 response is returned, AgentAPI has detected that the agent started processing the message
• GET /status – returns the current status of the agent, either “stable” or “running”
• GET /events – an SSE stream of events from the agent: message and status updates

Attach to a running agent’s terminal session.

agentapi attach --url localhost:3284

Press ctrl+c to detach from the session.

AgentAPI runs an in-memory terminal emulator. It translates API calls into appropriate terminal keystrokes and parses the agent’s outputs into individual messages.

There are 2 types of messages:

• User messages: sent by the user to the agent
• Agent messages: sent by the agent to the user

To parse individual messages from the terminal output, we take the following steps:

1. The initial terminal output, before any user messages are sent, is treated as the agent’s first message.
2. When the user sends a message through the API, a snapshot of the terminal is taken befo