A Gradio-based WebUI that lets users interact with the browser-use agent through a graphical interface. Users supply API keys and browser paths to operate automated browser tasks, with support for multiple language model providers and persistent browser sessions.
Project overview
Provides a graphical web interface designed to simplify user interaction with automated browser agents, including the ability to use existing browser profiles to maintain login states.
Project type
AI Agent
Use cases
Automation
Deployment
Refer to project documentation
License
MIT
Best for
General users who need a graphical web interface to operate browser agents and monitor automated web tasks.
Key capabilities
Provides a user-friendly interface for interacting with the browser agent and supports most browser-use functionality.
Supports Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama, and other LLMs.
Lets users use their own browser to avoid re-login and authentication challenges, with high-definition screen recording support.
Lets users keep the browser window open between AI tasks to retain interaction history and state.
Provides a VNC Viewer endpoint for watching browser interactions in the Docker Compose route.
Limitations and risks
When using the Own Browser feature with Chrome data, the WebUI must be opened in a non-Chrome browser such as Firefox or Edge.
GPU requirements, minimum hardware, telemetry, and coding requirements are not documented.
No direct end-to-end data boundary fact is documented. Local execution proves only that the named component can run locally; inference depends on configured external language models.
Getting started
Setup requires configuring API keys, environment settings, the browser executable path, and the browser user-data directory. Detailed setup difficulty and first success path are not documented.
Alternatives and comparisons
A self-improving AI agent that creates skills from experience and operates via a terminal UI, contrasting with the Gradio WebUI browser focus.
A platform to build and deploy AI agents and workflows using a visual canvas with source-available flexibility.
Small, composable engineering skills for AI coding agents to enforce software engineering fundamentals.
README: **WebUI:** is built on Gradio and supports most of `browser-use` functionalities. This UI is designed to be user-friendly and enables easy interaction with the browser agent.
README: **Expanded LLM Support:** We've integrated support for various Large Language Models (LLMs), including: Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama etc. And we plan…
README: **Custom Browser Support:** You can use your own browser with our tool, eliminating the need to re-login to sites or deal with other authentication challenges. This feature also s…
README: **Persistent Browser Sessions:** You can choose to keep the browser window open between AI tasks, allowing you to see the complete history and state of AI interactions.
README: 2. Open `.env` in your preferred text editor and add your API keys and other settings