{"repo":"browser-use/web-ui","free":true,"listed":false,"github":"https://github.com/browser-use/web-ui","clone":"git clone https://github.com/browser-use/web-ui.git","description":"🖥️ Run AI Agent in your browser.","language":"Python","stars":16280,"topics":["ai-agent","browser-automation","browser-use-box","cloud-browser"],"license":"MIT","category":"ai_agent_tool","readme_excerpt":"![\"Browser](\"./assets/web-ui.png\")
\n\n
\n\n[](https://github.com/browser-use/web-ui/stargazers)\n[](https://link.browser-use.com/discord)\n[](https://docs.browser-use.com)\n[](https://x.com/warmshao)\n\nThis project builds upon the foundation of the [browser-use](https://github.com/browser-use/browser-use), which is designed to make websites accessible for AI agents.\n\nWe would like to officially thank [WarmShao](https://github.com/warmshao) for his contribution to this project.\n\n**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.\n\n**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.\n\n**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.\n\n**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.\n\n\n\n## Installation Guide\n\n### Option 1: Local Installation\n\nRead the [quickstart guide](https://docs.browser-use.com/quickstart#prepare-the-environment) or follow the steps below to get started.\n\n#### Step 1: Clone the Repository\n```bash\ngit clone https://github.com/browser-use/web-ui.git\ncd web-ui\n```\n\n#### Step 2: Set Up Python Environment\nWe recommend using [uv](https://docs.astral.sh/uv/) for managing the Python environment.\n\nUsing uv (recommended):\n```bash\nuv venv --python 3.11\n```\n\nActivate the virtual environment:\n- Windows (Command Prompt):\n```cmd\n.venv\\Scripts\\activate\n```\n- Windows (PowerShell):\n```powershell\n.\\.venv\\Scripts\\Activate.ps1\n```\n- macOS/Linux:\n```bash\nsource .venv/bin/activate\n```\n\n#### Step 3: Install Dependencies\nInstall Python packages:\n```bash\nuv pip install -r requirements.txt\n```\n\nInstall Browsers in playwright. \n```bash\nplaywright install --with-deps\n```\nOr you can install specific browsers by running:\n```bash\nplaywright install chromium --with-deps\n```\n\n#### Step 4: Configure Environment\n1. Create a copy of the example environment file:\n- Windows (Command Prompt):\n```bash\ncopy .env.example .env\n```\n- macOS/Linux/Windows (PowerShell):\n```bash\ncp .env.example .env\n```\n2. Open `.env` in your preferred text editor and add your API keys and other settings\n\n#### Step 5: Enjoy the web-ui\n1. **Run the WebUI:**\n ```bash\n python webui.py --ip 127.0.0.1 --port 7788\n ```\n2. **Access the WebUI:** Open your web browser and navigate to `http://127.0.0.1:7788`.\n3. **Using Your Own Browser(Optional):**\n - 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.\n - Windows\n ```env\n BROWSER_PATH=\"C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe\"\n BROWSER_USER_DATA=\"C:\\Users\\YourUsername\\AppData\\Local\\Google\\Chrome\\User Data\"\n ```\n > Note: Replace `YourUsername` with your actual Windows username for Windows systems.\n - Mac\n ```env\n BROWSER_PATH=\"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome\"\n BROWSER_USER_DATA=\"/Users/YourUsername/Library/Application Support/Google/Chrome\"\n ```\n - Close all Chrome windows\n - 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.\n - Check the \"Use Own Browser\" option within the Browser Settings.\n\n### Option 2: Docker Installation\n\n#### Prerequisites\n- Docker and Docker Compose installed\n - [Docker Desktop](https://www.docker.com/products/docker-desktop/) (For Windows/macOS)\n - [Docker Engine](https://docs.docker.com/engine/install/) and [Docker Compose](https://docs.docker.com/compose/install/) (For Linux)\n\n#### Step 1: Clone the Repository\n```bash\ngit clone https://github.com/browser-use/web-ui.git\ncd web-ui\n```\n\n#### Step 2: Configure Environment\n1. Create a copy of the example environment file:\n- Windows (Command Prompt):\n```bash\ncopy .env.example .env\n```\n- macOS/Linux/Windows (PowerShell):\n```bash\ncp .env.example .env\n```\n2. Open `.env` in your preferred text editor and add your API keys and other settings\n\n#### Step 3: Docker Build and Run\n```bash\ndocker compose up --build\n```\nFor ARM64 systems (e.g., Apple Silicon Macs), please run follow command:\n```bash\nTARGETPLATFORM=linux/arm64 docker compose up --build\n```\n\n#### Step 4: Enjoy the web-ui and vnc\n- Web-UI: Open `http://localhost:7788` in your browser\n- VNC Viewer (for watching browser interactions): Open `http://localhost:6080/vnc.html`\n - Default VNC password: \"youvncpassword\"\n - Can be changed by setting `VNC_PASSWORD` in your `.env` file\n\n## Changelog\n- [x] **2025/01/26:** Thanks to @vvincent1234. Now browser-use-webui can combine with DeepSeek-r1 to engage in deep thinking!\n- [x] **2025/01/10:** Thanks to @casistack. Now we have Docker Setup option and also Support keep browser open between tasks.[Video tutorial demo](https://github.com/browser-use/web-ui/issues/1#issuecomment-2582511750).\n- [x] **2025/01/06:** Thanks to @richard-devbot. A New and Well-Designed WebUI is released. [Video tutorial demo](https://github.com/warmshao/browser-use-webui/issues/1#issuecomment-2573393113).\n","default_branch":"main","files":42,"tree":[".dockerignore",".env.example",".github/workflows/build.yml",".gitignore",".vscode/settings.json","Dockerfile","LICENSE","README.md","SECURITY.md","assets/examples/test.png","assets/web-ui.png","docker-compose.yml","requirements.txt","src/__init__.py","src/agent/__init__.py","src/agent/browser_use/browser_use_agent.py","src/agent/deep_research/deep_research_agent.py","src/browser/__init__.py","src/browser/custom_browser.py","src/browser/custom_context.py","src/controller/__init__.py","src/controller/custom_controller.py","src/utils/__init__.py","src/utils/config.py","src/utils/llm_provider.py","src/utils/mcp_client.py","src/utils/utils.py","src/webui/__init__.py","src/webui/components/__init__.py","src/webui/components/agent_settings_tab.py","src/webui/components/browser_settings_tab.py","src/webui/components/browser_use_agent_tab.py","src/webui/components/deep_research_agent_tab.py","src/webui/components/load_save_config_tab.py","src/webui/interface.py","src/webui/webui_manager.py","supervisord.conf","tests/test_agents.py","tests/test_controller.py","tests/test_llm_api.py","tests/test_playwright.py","webui.py"],"storefront":"/r/browser-use","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/browser-use/web-ui/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}