Open Operator

Open Operator is an open source project inspired by OpenAI's Operator feature, bringing autonomous web browsing capabilities to everyone. Built with Next.js and powered by Browserbase's web automation technology, it enables AI agents to interact with web interfaces naturally and effectively.

Features

• 🌐 Autonomous web browsing and interaction
• 🤖 Natural language interface for web navigation
• 🔄 Real-time browser state synchronization
• 🛠️ Extensible architecture for custom actions
• 📱 Responsive design for all devices
• 🎭 Reliable browser automation with Stagehand
• 🔍 Precise DOM understanding and manipulation

Getting Started

First, install the dependencies:

npm install
# or
yarn install
# or
pnpm install

Next, copy the example environment variables:

cp .env.example .env.local

You'll need to set up your API keys:

1. Get your OpenAI API key from OpenAI's dashboard
2. Get your Browserbase API key and project ID from Browserbase

Update .env.local with your API keys:

• OPENAI_API_KEY: Your OpenAI API key
• BROWSERBASE_API_KEY: Your Browserbase API key
• BROWSERBASE_PROJECT_ID: Your Browserbase project ID

Then, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev

Open http://localhost:3000 with your browser to see Open Operator in action.

How It Works

Open Operator uses a combination of AI models and advanced browser automation to enable natural web interactions:

1. Understanding Intent: Natural language processing to understand user intentions
2. Browser Automation: Leverages Browserbase's technology for reliable web interaction
3. DOM Management: Uses Stagehand for precise DOM traversal and manipulation
4. Action Execution: Translates intentions into precise browser actions
5. Real-time Feedback: Provides immediate visual and textual feedback

The system combines these technologies to:

• Parse and understand natural language commands
• Navigate and interact with web interfaces
• Execute complex sequences of actions
• Provide real-time feedback and results

Key Technologies

• Browserbase: Powers the core browser automation and interaction capabilities
• Stagehand: Handles precise DOM manipulation and state management
• Next.js: Provides the modern web framework foundation
• AI Models: Enable natural language understanding and decision making

Contributing

We welcome contributions! Whether it's:

• Adding new features
• Improving documentation
• Reporting bugs
• Suggesting enhancements

Please feel free to open issues and pull requests.

License

Open Operator is open source software licensed under the MIT license.

Acknowledgments

This project is inspired by OpenAI's Operator feature and builds upon various open source technologies including Next.js, React, Browserbase, and Stagehand.