web-ui: Open Source AI Development Platforms

What is web-ui?

web-ui is a MIT-licensed Gradio web interface that runs an AI browser agent in a local browser page, built for developers and teams who want to drive browser-use agents interactively instead of writing Python for every task.

What it is

web-ui is a Python project that wraps the browser-use library in a Gradio front end, exposing most of browser-use's functionality through a local web page rather than a code interface. It supports multiple large language model providers, lets the agent attach to an existing browser installation, and keeps a browser session alive across tasks. The project lives in the AI and machine learning space under AI development platforms, is written in Python, and is distributed under the MIT licence.

The concrete problem it solves is friction. Standing up a browser agent with browser-use alone means writing and re-running code, wiring API keys by hand, and re-authenticating to every site the agent touches. web-ui replaces that loop with a single command that serves a UI on http://127.0.0.1:7788, where the agent task, model choice, and browser settings are configured in the page. Its custom browser support points the agent at an existing Chrome profile through BROWSER_PATH and BROWSER_USER_DATA, so logged-in sessions carry over and the user does not have to sign in again. Persistent browser sessions keep the window open between AI tasks, so the full history and state of the interaction stay visible rather than disappearing when a task ends.

Key capabilities

Gradio web UI started with python webui.py --ip 127.0.0.1 --port 7788 and reached at http://127.0.0.1:7788.
Expanded LLM support configured through a .env file, covering Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, and Ollama.
Custom browser support using BROWSER_PATH and BROWSER_USER_DATA to run against the user's own Chrome installation and its user data directory.
Persistent browser sessions that hold the browser window open across AI tasks and preserve the complete interaction history and state.
High-definition screen recording of agent runs.
Docker and Docker Compose deployment as an alternative to the local installation path.
Playwright browser installation through playwright install --with-deps, or playwright install chromium --with-deps to install only Chromium.

Who uses it and how

Developers already using browser-use who want a UI layer over the library instead of re-authoring scripts for each task.
Operators running local models through Ollama, who need an agent interface without depending on a hosted model provider.
Teams standardised on Azure OpenAI, Anthropic, or Google, who need to select among providers from one interface.
Users automating sites where they are already signed in, where the custom browser path reuses the Chrome profile instead of forcing a fresh login.
Self-hosters on Windows, macOS, or Linux, for whom the documentation gives explicit Chrome executable and user data paths per platform.

The project's 16,566 stars and 2,757 forks indicate broad individual adoption alongside its library dependency.

Getting started

Clone the repository, create a Python 3.11 environment with uv venv --python 3.11, install requirements.txt with uv, run playwright install --with-deps, copy .env.example to .env and add API keys, then launch with python webui.py --ip 127.0.0.1 --port 7788. A Docker and Docker Compose path exists as an alternative for those who prefer containerised deployment.

How it compares

The only comparable tool named in the facts is browser-use itself, which this project builds upon: browser-use makes websites accessible to AI agents and provides the agent engine, while web-ui supplies a Gradio front end over that engine. Where browser-use is driven from code, web-ui is driven from a browser tab, and it adds own-browser attachment and persistent sessions on top of the underlying library.

When to use it — and when not to

A self-hoster must operate a Python 3.11 environment, install Playwright browsers, and supply API keys for whichever model provider is chosen; custom browser mode additionally requires closing all Chrome windows and opening the interface in a different browser such as Firefox or Edge, because the persistent context consumes the Chrome data directory. It is a poor fit for anyone wanting a hosted, zero-install service with managed credentials. The README excerpt is thin, the Docker section is truncated and its prerequisite list incomplete, and the repository carries 324 open issues, so plan for troubleshooting time.

project readme (upstream, from github) — read inline

This project builds upon the foundation of the browser-use, which is designed to make websites accessible for AI agents.

We would like to officially thank WarmShao for his contribution to this project.

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.

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 to add support for even more models in the future.

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 supports high-definition screen recording.

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.

Your browser does not support playing this video!

Installation Guide

Option 1: Local Installation

Read the quickstart guide or follow the steps below to get started.

Step 1: Clone the Repository

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

Step 2: Set Up Python Environment

We recommend using uv for managing the Python environment.

Using uv (recommended):

uv venv --python 3.11

Activate the virtual environment:

Windows (Command Prompt):

.venv\Scripts\activate

Windows (PowerShell):

.\.venv\Scripts\Activate.ps1

macOS/Linux:

source .venv/bin/activate

Step 3: Install Dependencies

Install Python packages:

uv pip install -r requirements.txt

Install Browsers in playwright.

playwright install --with-deps

Or you can install specific browsers by running:

playwright install chromium --with-deps

Step 4: Configure Environment

Create a copy of the example environment file:

Windows (Command Prompt):

copy .env.example .env

macOS/Linux/Windows (PowerShell):

cp .env.example .env

Open .env in your preferred text editor and add your API keys and other settings

Step 5: Enjoy the web-ui

Run the WebUI:

python webui.py --ip 127.0.0.1 --port 7788

Access the WebUI: Open your web browser and navigate to http://127.0.0.1:7788.
Using Your Own Browser(Optional):
- Set BROWSER_PATH to the executable path of your browser and BROWSER_USER_DATA to the user data directory of your browser. Leave BROWSER_USER_DATA empty if you want to use local user data.
  - Windows
```
 BROWSER_PATH="C:\Program Files\Google\Chrome\Application\chrome.exe"
 BROWSER_USER_DATA="C:\Users\YourUsername\AppData\Local\Google\Chrome\User Data"
```
    Note: Replace YourUsername with your actual Windows username for Windows systems.
  - Mac
```
 BROWSER_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
 BROWSER_USER_DATA="/Users/YourUsername/Library/Application Support/Google/Chrome"
```
- Close all Chrome windows
- Open the WebUI in a non-Chrome browser, such as Firefox or Edge. This is important because the persistent browser context will use the Chrome data when running the agent.
- Check the "Use Own Browser" option within the Browser Settings.

Option 2: Docker Installation

Prerequisites

Docker and Docker Compose installed
- Docker Desktop (For Windows/macOS)
- Docker Engine and Docker Compose (For Linux)

Step 1: Clone the Repository

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

Step 2: Configure Environment

Create a copy of the example environment file:

Windows (Command Prompt):

copy .env.example .env

macOS/Linux/Windows (PowerShell):

cp .env.example .env

Open .env in your preferred text editor and add your API keys and other settings

Step 3: Docker Build and Run

docker compose up --build

For ARM64 systems (e.g., Apple Silicon Macs), please run follow command:

TARGETPLATFORM=linux/arm64 docker compose up --build

Step 4: Enjoy the web-ui and vnc

Web-UI: Open http://localhost:7788 in your browser
VNC Viewer (for watching browser interactions): Open http://localhost:6080/vnc.html
- Default VNC password: "youvncpassword"
- Can be changed by setting VNC_PASSWORD in your .env file

Changelog

2025/01/26: Thanks to @vvincent1234. Now browser-use-webui can combine with DeepSeek-r1 to engage in deep thinking!
2025/01/10: Thanks to @casistack. Now we have Docker Setup option and also Support keep browser open between tasks.Video tutorial demo.
2025/01/06: Thanks to @richard-devbot. A New and Well-Designed WebUI is released. Video tutorial demo.

Frequently asked questions

Is web-ui free to use?

web-ui is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does web-ui do?

🖥️ Run AI Agent in your browser.

What is web-ui written in?

web-ui is primarily written in Python. Its source is publicly available at https://github.com/browser-use/web-ui, and it has 16,566 GitHub stars.