import AcpQuickstartPy from '/snippets/code-samples/acp-quickstart-py.mdx'; import AcpDeepAgentsServerJs from '/snippets/code-samples/acp-deep-agents-server-js.mdx'; import AcpMultipleAgentsJs from '/snippets/code-samples/acp-multiple-agents-js.mdx'; import AcpSlashCommandsJs from '/snippets/code-samples/acp-slash-commands-js.mdx'; import AcpHitlJs from '/snippets/code-samples/acp-hitl-js.mdx'; import AcpCustomToolsJs from '/snippets/code-samples/acp-custom-tools-js.mdx'; import AcpCustomBackendJs from '/snippets/code-samples/acp-custom-backend-js.mdx';

Agent Client Protocol (ACP) standardizes communication between coding agents and code editors or IDEs. With the ACP protocol, you can make use of your custom deep agents with any ACP-compatible client, allowing your code editor to provide project context and receive rich updates.

Install the ACP integration package:

:::python

pip install deepagents-acp

uv add deepagents-acp

:::js

npm install deepagents-acp

yarn add deepagents-acp

pnpm add deepagents-acp

Then expose a deep agent over ACP.

This starts an ACP server in stdio mode (it reads requests from stdin and writes responses to stdout). In practice, you usually run this as a command launched by an ACP client (for example, your editor), which then communicates with the server over stdio.

:::python

:::

:::js

import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "coding-assistant",
    description: "AI coding assistant with filesystem access",
  },
  workspaceRoot: process.cwd(),
});

You can also use the CLI without writing any code:

npx deepagents-acp

:::

:::python The deepagents-acp package includes an example coding agent with filesystem and shell that you can run out of the box. :::

:::js The deepagents-acp package provides both a CLI and a programmatic API for exposing deep agents over ACP. :::

Deep agents work anywhere you can run an ACP agent server. Some notable ACP clients include:

• Zed
• JetBrains IDEs
• Visual Studio Code (via vscode-acp)
• Neovim (via ACP-compatible plugins)

:::python

The deepagents repo includes a demo ACP entrypoint you can register with Zed:

1. Clone the deepagents repo and install dependencies:

git clone https://github.com/langchain-ai/deepagents.git
cd deepagents/libs/acp
uv sync --all-groups
chmod +x run_demo_agent.sh

2. Configure credentials for the demo agent:

cp .env.example .env

Then set ANTHROPIC_API_KEY in .env.

3. Configure your ACP agent server command in Zed's settings.json:

{
  "agent_servers": {
    "DeepAgents": {
      "type": "custom",
      "command": "/your/absolute/path/to/deepagents/libs/acp/run_demo_agent.sh"
    }
  }
}

4. Open Zed's Agents panel and start a Deep Agents thread.

:::

:::js

Register your deep agent with Zed by adding it to your Zed settings (~/.config/zed/settings.json on Linux, ~/Library/Application Support/Zed/settings.json on macOS):

Simple setup (no code required):

{
  "agent": {
    "profiles": {
      "deepagents": {
        "name": "DeepAgents",
        "command": "npx",
        "args": ["deepagents-acp"],
        "env": {
          "ANTHROPIC_API_KEY": "sk-ant-..."
        }
      }
    }
  }
}

With CLI options:

{
  "agent": {
    "profiles": {
      "deepagents": {
        "name": "DeepAgents",
        "command": "npx",
        "args": [
          "deepagents-acp",
          "--name", "my-assistant",
          "--skills", "./skills",
          "--debug"
        ],
        "env": {
          "ANTHROPIC_API_KEY": "sk-ant-..."
        }
      }
    }
  }
}

Custom server script:

For more control, create a TypeScript server script:

// server.ts
import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "my-agent",
    description: "My custom coding agent",
    skills: ["./skills/"],
  },
});

Then point Zed at it:

{
  "agent": {
    "profiles": {
      "my-agent": {
        "name": "My Agent",
        "command": "npx",
        "args": ["tsx", "./server.ts"]
      }
    }
  }
}

Open Zed's Agents panel and start a Deep Agents thread.

:::

:::python

If you want to run an ACP agent server as a local dev tool, you can use Toad to manage the process.

uv tool install -U batrachian-toad

toad acp "python path/to/your_server.py" .
# or
toad acp "uv run python path/to/your_server.py" .

:::

:::js

Deep Agents is available in the ACP Agent Registry for one-click installation in Zed and JetBrains IDEs. When an ACP client supports the registry, users can discover and install Deep Agents without any manual configuration.

:::

:::js

The CLI is the fastest way to start an ACP server. It requires no code—just run npx deepagents-acp and connect your editor.

npx deepagents-acp [options]

:::

:::js

Convenience function to create and start a server in one call:

import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "coding-assistant",
    description: "AI coding assistant with filesystem access",
  },
  workspaceRoot: process.cwd(),
});

For full control, use the DeepAgentsServer class directly:

:::

:::js

You can expose multiple agents from a single server. The ACP client selects which agent to use when creating a session:

The server registers built-in slash commands with the IDE: /plan, /agent, /ask, /clear, and /status. You can also define custom commands per agent:

Use interruptOn to require user approval in the IDE before the agent runs sensitive tools:

When the agent calls a protected tool, the IDE prompts the user to allow or reject the operation, with options to remember the decision for the session.

import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "project-agent",
    description: "Agent with project-specific knowledge",
    skills: ["./skills/", "~/.deepagents/skills/"],
    memory: ["./.deepagents/AGENTS.md"],
  },
  workspaceRoot: process.cwd(),
});

:::