AI/TLDR

Browser Use Web UI

A Gradio web interface for running browser-use AI agents in your browser

Overview

Browser Use Web UI is a graphical front end for the browser-use project, which makes websites accessible to AI agents. Instead of writing code, you interact with the browser agent through a simple web page built on Gradio, making it easier to give tasks and watch the agent work.

The tool supports many large language models, including Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, and Ollama. You can also connect your own browser so the agent reuses your existing logins, and you can keep the browser window open between tasks to review the full history of what the agent did.

What it does

  • Gradio-based web interface that supports most browser-use functionality without writing code
  • Works with many LLM providers, including Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, and Ollama
  • Use your own browser so the agent reuses existing logins and avoids extra authentication steps
  • Persistent browser sessions that keep the window open between tasks to review state and history
  • High-definition screen recording of browser interactions when using your own browser
  • Docker setup with a VNC viewer so you can watch the agent work inside a container

Getting started

You can run Browser Use Web UI with a local Python install or with Docker. The local path uses uv to manage the Python environment, then launches the Gradio web app.

Clone the repository

Download the project source and move into the new folder.

bashbash
git clone https://github.com/browser-use/web-ui.git
cd web-ui

Set up the Python environment

Create a virtual environment with uv using Python 3.11, then activate it (the example below shows macOS/Linux).

bashbash
uv venv --python 3.11
source .venv/bin/activate

Install dependencies and browsers

Install the Python packages, then install the Playwright browsers the agent drives.

bashbash
uv pip install -r requirements.txt
playwright install --with-deps

Configure and run the WebUI

Copy the example environment file and add your API keys, then start the web app and open it at http://127.0.0.1:7788.

bashbash
cp .env.example .env
python webui.py --ip 127.0.0.1 --port 7788

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

When to use it

  • Give an AI agent plain-language web tasks through a UI instead of writing automation code
  • Compare how different LLM providers, such as OpenAI, Anthropic, or DeepSeek, handle the same browsing task
  • Run automation against sites you are already logged into by connecting your own browser
  • Watch and review agent browser sessions, including via the Docker VNC viewer

How Browser Use Web UI compares

Browser Use Web UI alongside other open-source computer & browser use tools AI/TLDR tracks, ranked by GitHub stars.

ToolStarsWhat it does
Browser Use★ 105kA Python library that lets agents control a real browser to read pages and complete tasks online from natural-language instructions.
Open Interpreter★ 65.9kA lightweight coding agent that runs code on your own computer to carry out tasks from natural-language requests.
UI-TARS Desktop★ 38kByteDance's multimodal agent stack and desktop app that controls a computer's graphical interface using vision-language models.
Stagehand★ 23.5kA TypeScript browser-automation SDK from Browserbase that mixes natural-language actions with normal code for reliable web agents.
Skyvern★ 22.4kA tool that uses language models and computer vision to automate browser workflows without writing custom code for each website.
Cua★ 19.9kInfrastructure for computer-use agents, providing sandboxes and SDKs that let agents control full desktops on macOS, Linux, and Windows.
Agent Zero★ 18.4kA general-purpose personal agent framework that uses the computer, terminal, and code as its main tools to complete tasks.
Browser Use Web UI★ 16.2kA Gradio web interface for running browser-use AI agents in your browser