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
unclecode/crawl4ai
Crawl4AI is an open-source Python library and CLI/Docker tool that turns arbitrary web pages into clean, structured Markdown suited for retrieval-augmented generation and AI agent pipelines. It runs an async browser pool across Chromium, Firefox and WebKit, with persistent profiles, remote CDP connections, session state, proxy rotation and a stealth mode for sites that detect automation. Markdown generation supports content filters (pruning, BM25, and LLM-based filtering) and automatic citation lists, while structured extraction covers CSS/XPath schemas, regex, an auto-generated schema helper, and LLM-driven extraction into typed JSON. Crawling strategies include BFS, DFS and best-first deep crawls with crash recovery, an adaptive crawler that stops once it has learned enough to answer a query, URL discovery from sitemaps and Common Crawl, full-page scrolling for lazy-loaded content, and capture of screenshots, PDFs, media and links. Beyond the self-hosted library and Docker server, the project offers a paid hosted cloud API exposing the same scrape/search/extract/answer operations without running a browser, and an MCP endpoint that lets coding agents such as Claude Code, Cursor and Codex call the crawler directly as a tool. It targets developers building RAG systems, data pipelines and autonomous agents that need reliable web-to-Markdown extraction, whether run locally, self-hosted, or via the hosted API.
https://github.com/unclecode/crawl4ai
Also in Browser Automation
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.
alibaba/page-agent
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
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.