browser-use/browser-use
Open-source browser automation agent for LLMs, usable as a Python library, CLI, hosted cloud service, or MCP server exposing browser-control tools.
Awesome MCP › Browser Automation
alibaba/page-agent
Page Agent is a JavaScript-based GUI agent designed to bring natural language control directly into web pages. It simplifies the creation of AI copilots and automates web workflows by allowing users to interact with web elements using text-based commands, directly within the browser tab. Unlike many other automation tools, it requires no browser extensions, external Python processes, or headless browsers, making integration straightforward via a single JavaScript snippet or NPM package. The agent focuses on text-based DOM manipulation, eliminating the need for screenshots or multi-modal LLMs with special permissions. Developers can bring their own LLMs, providing flexibility in model choice. Use cases include building SaaS AI copilots, automating form filling in ERP/CRM systems, enhancing web accessibility through natural language, and enabling multi-page agent capabilities with an optional Chrome extension. It also offers an MCP Server (Beta) for external control. The project emphasizes client-side web enhancement over server-side automation and builds on the `browser-use` project's DOM processing components.
https://github.com/alibaba/page-agent
Also in Browser Automation
unclecode/crawl4ai
Open-source async web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an official MCP server for AI assistants.
microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
Skyvern-AI/skyvern
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
browser-use/browser-harness
MCP-compatible harness that lets coding agents drive a user's real, logged-in Chrome browser over the DevTools Protocol, writing new helper scripts as it works.
apify/actors-mcp-server
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.
AgentDeskAI/browser-tools-mcp
BrowserTools MCP is a powerful browser monitoring and interaction tool that leverages the Model Context Protocol to enable AI-powered applications to capture and analyze browser data directly within MCP-compatible IDEs.