🌐 Browser-Use

Open-Source Web Automation with LLMs

Let LLMs interact with websites naturally

Key Features • Live Demos • Quick Start • Examples • Models

---

🎥 Live Demos

Watch Browser-Use tackle real-world tasks:

Job Applications Apply to 5 SF tech jobs

Multi-Tab Search Find images across tabs

Flight Search Find cheapest flights

🚀 Key Features

• 🤖 Universal LLM Support - Works with any Language Model
• 🎯 Smart Element Detection - Automatically finds interactive elements
• 📑 Multi-Tab Management - Seamless handling of browser tabs
• 🔍 XPath Extraction - No more manual DevTools inspection
• 👁️ Vision Model Support - Process visual page information
• 🛠️ Customizable Actions - Add your own browser interactions

💻 Quick Start

# Install with uv (recommended)
uv pip install -r requirements.txt

# Generate requirements
uv pipreqs --ignore .venv --force

📝 Examples

from browser_use import AgentService, ControllerService
from langchain_anthropic import ChatAnthropic

# Initialize browser agent
agent = AgentService(
    task="Find cheapest flight from London to Kyrgyzstan",
    model=ChatAnthropic(model="claude-3-sonnet"),
    controller=ControllerService(),
    use_vision=True
)

# Let it work its magic
await agent.run()

🤖 Supported Models

GPT-4o

GPT-4o Mini

Claude 3.5 Sonnet

🤝 Contributing

Contributions are welcome!

---

Star ⭐ this repo if you find it useful!
Made with ❤️ by the Browser-Use team