browser-use/web-ui

🖥️ Run AI Agent in your browser.

What it solves

This project provides a user-friendly graphical interface for the browser-use library, allowing users to interact with AI agents that can navigate and use websites. It removes the need for writing code to trigger agentic browser automation tasks.

How it works

Built on Gradio, the WebUI serves as a control panel for the browser agent. It integrates with various Large Language Models (LLMs) such as Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, and Ollama. Users can configure the agent to use a custom local browser instance to maintain authentication sessions and avoid re-logging into websites.

Who it’s for

Users who want to operate AI browser agents without needing to write Python scripts, as well as developers who want a visual way to monitor and manage their browser-automation agents.

Highlights

  • Broad LLM Support: Compatible with a wide range of providers including DeepSeek, Anthropic, and Ollama.
  • Custom Browser Integration: Ability to use a local browser executable and user data directory to bypass authentication hurdles.
  • Persistent Sessions: Option to keep the browser window open between different AI tasks to maintain state.
  • Detailed Monitoring: Supports high-definition screen recording and VNC viewer access when running via Docker.

Related

  • Project
    browser-use/browser-use

    A library and framework that enables AI agents to control a web browser like a human to automate tasks such as filling forms and extracting data.

  • Project
    webbrain-one/webbrain

    An open-source AI browser agent extension that automates web tasks, extracts data, and runs multi-step workflows using local or cloud LLMs.

  • Project
    alibaba/page-agent

    A JavaScript library that embeds an AI agent directly into web pages for text-based DOM manipulation and automation of web workflows via natural language.

  • Project
    platonai/Browser4

    Browser4 is an AI‑native browser automation platform. It offers a Rust‑based backend and a human‑friendly CLI (`browser4‑cli`) that lets humans or LLM‑driven agents open real Chromium sessions, interact with pages (click, fill, wait, etc.), and extract data via deterministic X‑SQL/CSS selectors or LLM‑assisted commands. It supports zero‑token, ML‑based spreadsheet generation (WebMiner), high‑throughput swarm crawling, and an extensible plugin/skill system, making it suitable for large‑scale web automation and autonomous agents.

  • Project
    open-webui/open-webui

    A feature-rich, self-hosted AI platform that provides a user-friendly interface for local and API-based LLMs, featuring built-in RAG and extensive plugin support.