browser-agents

Browser Agents - AI Browser Automation Platform

Browser Agents is a comprehensive web platform that lets you create, deploy, and manage AI-powered browser automation agents. Build intelligent bots that can navigate websites, extract data, fill forms, and perform complex web tasks using natural language instructions through a modern dashboard interface.

License Python Docker PRs Welcome

🚀 Quick Start

  1. Clone and start:
    git clone https://github.com/daviddaytw/browser-agents.git
    cd browser-agents
    docker-compose up --build
    
  2. Access the platform:
    • Dashboard: http://localhost:3000
    • API: http://localhost:8000/docs

🏗️ Architecture

Browser Agents consists of two main components:

🐳 Browser Pod (/browser-pod)

FastAPI microservice that handles browser automation:

🎛️ Dashboard (/dashboard)

Next.js web application for task management:

📖 Usage

  1. Open the dashboard at http://localhost:3000
  2. Create a task template describing what you want to automate
  3. Execute the task and monitor progress in real-time
  4. Download results and media captures
Configuration ### Environment Variables - `OPENAI_API_KEY` - Your OpenAI API key - `ANTHROPIC_API_KEY` - Your Anthropic API key - `DATABASE_URL` - PostgreSQL connection string

🤝 Contributing

We welcome contributions! See our Contributing Guide for details.

Quick steps:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

📄 License

Licensed under the Apache License 2.0.

🙏 Acknowledgments


**Made with ❤️ by the [David Day](https://github.com/daviddaytw)** [⭐ Star us on GitHub](https://github.com/daviddaytw/browser-agents) • [🐛 Report Issues](https://github.com/daviddaytw/browser-agents/issues)