ScriptsApr 6, 2026·3 min read

Browser-Use Web UI — Visual AI Browser Automation

Gradio-based web interface for Browser-Use AI agent. Automate web browsing with visual feedback, persistent sessions, and HD recording. Supports 6+ LLM providers. 15,800+ stars, MIT.

SC
Script Depot · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

Local:

git clone https://github.com/browser-use/web-ui.git
cd web-ui
python -m venv .venv && source .venv/bin/activate
uv pip install -r requirements.txt
playwright install --with-deps
cp .env.example .env  # Add your API keys
python webui.py --ip 127.0.0.1 --port 7788

Docker:

git clone https://github.com/browser-use/web-ui.git
cd web-ui && cp .env.example .env
docker compose up --build

Access at http://localhost:7788.

Intro

Browser-Use Web UI is a Gradio-based visual interface for the Browser-Use AI agent framework, with 15,800+ GitHub stars and MIT license. It lets you automate web browsing tasks through a point-and-click interface — watch the AI navigate websites in real-time with HD screen recording, maintain persistent browser sessions (no re-login), and use your existing Chrome profile. Supports 6+ LLM providers including OpenAI, Anthropic, Google, DeepSeek, and local models via Ollama. While Browser-Use itself is a Python library, this Web UI makes it accessible to anyone.

Best for: developers and non-technical users who want visual AI browser automation without writing code. Works with: OpenAI, Anthropic, Google, Azure OpenAI, DeepSeek, Ollama. Setup time: under 5 minutes.

Browser-Use Web UI — Features

Core Capabilities

  • Visual Task Execution — Type a task in natural language, watch the AI browse
  • Persistent Browser Sessions — Keep logged-in state across tasks
  • Custom Chrome Profile — Use your existing browser with all cookies and extensions
  • HD Screen Recording — Record every automation session for review
  • Multi-Tab Support — AI can open and manage multiple browser tabs
  • File Downloads — AI can download files during automation

Supported LLM Providers

Provider Models
OpenAI GPT-4o, GPT-4o-mini
Anthropic Claude Opus, Sonnet
Google Gemini 2.0 Flash, Pro
Azure OpenAI Any deployed model
DeepSeek DeepSeek Chat
Ollama Any local model

Web UI vs CLI

Feature Web UI CLI
Interface Gradio visual UI Command line
Screen recording Built-in HD Optional
Browser profile Custom Chrome Playwright default
Best for Visual tasks, demos Scripted automation
Learning curve Low Medium

Docker with VNC

When running via Docker, you can monitor the browser remotely via VNC viewer — useful for headless servers.

Example Tasks

"Go to Amazon, search for wireless headphones under $50, and save the top 3 results"
"Log into my GitHub, create a new issue in repo X with title Y"
"Fill out the contact form on example.com with my details"
"Take a screenshot of the pricing page on competitor.com"

FAQ

Q: What is Browser-Use Web UI? A: A visual web interface for the Browser-Use AI browser automation framework. Type tasks in natural language, watch the AI browse websites in real-time.

Q: Is it free? A: Yes, MIT license. You provide your own LLM API keys.

Q: Can I use my existing Chrome profile? A: Yes, configure the Chrome profile path in settings to use existing cookies and logged-in sessions.

🙏

Source & Thanks

Created by Browser-Use. Licensed under MIT.

web-ui — ⭐ 15,800+

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

mcp2cli — Turn MCP Servers into CLI Tools, Zero Codegen

Convert any MCP server, OpenAPI spec, or GraphQL endpoint into a full CLI at runtime. Saves 96-99% of tokens wasted on tool schemas every turn.

MCP Hub
◈Home🔍Search👤Me