actionbook

Table of Contents

• Why Actionbook?
• Quick Start
• Installation
• Usage Examples
• Available Tools
• Development
• Contributing

Why Actionbook?

❌ Without Actionbook

Building reliable browser agents is difficult and expensive:

• Slow Execution: Agents waste time parsing full HTML pages to find elements.
• High Token Costs: Sending entire DOM trees to LLMs consumes massive context windows.
• Brittle Selectors: Updates to website UIs break hardcoded selectors and agent logic immediately.
• Hallucinations: LLMs often guess incorrect actions when faced with complex, unstructured DOMs.

✅ With Actionbook

Actionbook places up-to-date action manuals with the relevant DOM selectors directly into your LLM's context.

• 10x Faster: Agents access pre-computed "Action manuals" to know exactly what to do without exploring.
• 100x Token Savings: Instead of whole HTML page, agents receive only related DOM elements in concise, semantic JSON definitions.
• Resilient Automation: Action manuals are maintained and versioned. If a site changes, the manual is updated, not your agent.
• Universal Compatibility: Works with any LLM (OpenAI, Anthropic, Gemini) and any AI operator framework.

See how Actionbook enables an agent to complete an Airbnb search task 10x faster.

https://github.com/user-attachments/assets/9f896fe7-296a-44b3-8592-931a099612de

Quick Start

Get started with Actionbook in under 2 minutes:

Step 1: Install the CLI

npm install -g @actionbookdev/cli

# Install browser (Chromium) for automation
actionbook browser install

Step 2: Use with any AI Agent

When working with any AI coding assistant (Claude Code, Cursor, etc.), add this to your prompt:

Use Actionbook to understand and operate the web page.

The agent will automatically use the CLI to fetch action manuals and execute browser operations.

Step 3 (Optional): Add the Skill

For enhanced agent integration, add the Actionbook skill:

npx skills add actionbook/actionbook

Installation

Actionbook provides three integration methods:

Prerequisites

Before installing, make sure you have:

• ✅ Node.js >= v18.0.0 (Download)

💡 Tip: Check your Node.js version with node --version

Note: Actionbook is currently in open beta. No API key required!

Option 1: CLI (Recommended)

Install the CLI globally to use Actionbook from the command line or with any AI agent.

npm install -g @actionbookdev/cli

# Install browser (Chromium) for automation
actionbook browser install

Basic Commands:

# Search for action manuals
actionbook search "airbnb search"

# Get action details by ID
actionbook get "site/airbnb.com/page/home/element/search-button"

# Browser automation
actionbook browser open airbnb.com
actionbook browser click '[data-testid="search-button"]'
actionbook browser fill 'input[name="location"]' 'Tokyo'

Option 2: MCP Server

Use this option if you're working with an MCP-compatible AI IDE.

{
  "mcpServers": {
    "actionbook": {
      "command": "npx",
      "args": ["-y", "@actionbookdev/mcp@latest"]
    }
  }
}

claude mcp add actionbook -- npx -y @actionbookdev/mcp@latest --api-key YOUR_API_KEY

{
  "mcp": {
    "servers": {
      "actionbook": {
        "command": "npx",
        "args": ["-y", "@actionbookdev/mcp@latest"]
      }
    }
  }
}