Repository files navigation

ControlClaude Code,Goose,Aider, andCodex 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. Installagentapi by downloading the latest release binary from thereleases page.

2. Verify the installation:

   agentapi --help

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

3. Run a Claude Code server (assumesclaude is installed on your system and in thePATH):

   agentapi server -- claude

   If you're getting an error thatclaude is not in thePATH but you can run it from your shell, trywhich 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 chat web interface athttp://localhost:3284/chat.

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 useagentapi to run the Aider and Goose agents:

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

An OpenAPI schema is available inopenapi.json.

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

Pressctrl+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 before any keystrokes are sent.
3. The user message is then submitted to the agent. From this point on, any time the terminal output changes, a new snapshot is taken. It's diffed against the initial snapshot, and any new text that appears below the initial content is treated as the agent's next message.
4. If the terminal output changes again before a new user message is sent, the agent message is updated.

This lets us split the terminal output into a sequence of messages.

Each agent message contains some extra bits that aren't useful to the end user:

• The user's input at the beginning of the message. Coding agents often echo the input back to the user to make it visible in the terminal.
• An input box at the end of the message. This is where the user usually types their input.

AgentAPI automatically removes these.

• For user input, we strip the lines that contain the text from the user's last message.
• For the input box, we look for lines at the end of the message that contain common TUI elements, like> or------.

Splitting the terminal output into a sequence of messages should still work, since it doesn't depend on the TUI structure. The logic for removing extra bits may need to be updated to account for new elements. AgentAPI will still be usable, but some extra TUI elements may become visible in the agent messages.

Pending feedback, we're considering the following features:

• Support the MCP protocol
• Support the Agent2Agent Protocol

In the short term, AgentAPI solves the problem of how to programmatically control coding agents. As time passes, we hope to see the major agents release proper SDKs. One might wonder whether AgentAPI will still be needed then. We think that depends on whether agent vendors decide to standardize on a common API, or each sticks with a proprietary format.

In the former case, we'll deprecate AgentAPI in favor of the official SDKs. In the latter case, our goal will be to make AgentAPI a universal adapter to control any coding agent, so a developer using AgentAPI can switch between agents without changing their code.