simonnsanita/browseruseapiv2

Browser-Use WebUI on Hugging Face Spaces

This is a deployment of the browser-use-webui project on Hugging Face Spaces, providing a user-friendly Gradio interface for browser automation using AI agents.

Features

• —Gradio-based WebUI: User-friendly interface built on Gradio
• —Multiple LLM Support: OpenAI, Anthropic, Google Gemini, DeepSeek, and more
• —Browser Automation: AI-powered web browsing and task automation
• —Real-time Interaction: Watch AI agents perform tasks in real-time

Usage

1. 1.Set your API keys in the Space settings (Environment Variables):
2. 2.OPENAI_API_KEY for OpenAI models
3. 3.ANTHROPIC_API_KEY for Anthropic models
4. 4.GOOGLE_API_KEY for Google Gemini models
5. 5.And other supported providers

1. 1.Open the Space and start using the web interface

1. 1.Enter your task description and select your preferred AI model

1. 1.Watch as the AI agent performs the task in the browser

Supported LLM Providers

• —OpenAI (GPT-4, GPT-3.5)
• —Anthropic (Claude)
• —Google (Gemini)
• —DeepSeek
• —Mistral
• —Ollama (for local models)
• —And many more...

Environment Variables

Set these in your Space settings under "Environment Variables":

• —OPENAI_API_KEY: Your OpenAI API key
• —ANTHROPIC_API_KEY: Your Anthropic API key
• —GOOGLE_API_KEY: Your Google API key
• —DEFAULT_LLM: Default LLM provider (e.g., "openai", "anthropic", "google")
• —BROWSER_USE_LOGGING_LEVEL: Logging level (info, debug, result)

Original Project

This Space is based on the excellent browser-use-webui project by the browser-use team.

License

MIT License - see the original project for details.