# 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.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

**Local:**
```bash
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:**
```bash
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](https://tokrepo.com/en/workflows/) 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](https://github.com/browser-use). Licensed under MIT.
>
> [web-ui](https://github.com/browser-use/web-ui) — ⭐ 15,800+

---

<!-- ZH -->


## Quick Use

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

Visit `http://localhost:7788`.

---

## Intro

Browser-Use Web UI is a Gradio-based visual AI browser automation interface with 15,800+ stars and an MIT license. Describe tasks in natural language and watch AI browse the web in real time. Supports persistent sessions, HD screen recording, and custom Chrome profiles. Works with 6+ LLM providers including OpenAI, Anthropic, Google, DeepSeek, and Ollama.

---

## Source & Thanks

> Created by [Browser-Use](https://github.com/browser-use). Licensed under MIT.
>
> [web-ui](https://github.com/browser-use/web-ui) — ⭐ 15,800+


---
Source: https://tokrepo.com/en/workflows/browser-use-web-ui-visual-ai-browser-automation-badeea82
Author: Browser Use