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
agent-infra/sandbox
The project agent-infra/sandbox is an all-in-one sandbox environment designed specifically for AI agents and developers. It integrates multiple essential tools and interfaces such as a web browser, shell terminal, file operations, VSCode server, Jupyter notebook, and Model Context Protocol (MCP) services into a single Docker container. This unified environment allows seamless interaction and coordination between these components, overcoming the limitations of traditional single-purpose sandboxes. The sandbox features a unified file system where files downloaded via the browser are instantly accessible in shell and file operations, enabling smooth workflows. It supports multiple interfaces including VNC for visual browser interaction, Chrome DevTools Protocol (CDP) for programmatic browser control, and MCP for high-level browser automation. The environment is pre-configured with MCP servers that provide APIs for browser automation, file system operations, shell command execution, document processing, and research paper access, making it agent-ready for AI integration. The sandbox ensures secure execution of Python and Node.js code with safety guarantees and requires zero configuration to get started. It supports SDKs in Python, TypeScript/JavaScript, and Golang, allowing developers to interact programmatically with the sandbox services. The project provides a quick start with a single Docker command and detailed documentation for usage. Its architecture is cloud-native and lightweight, designed to provide a secure, unified, and developer-friendly environment for AI agent development and testing. Overall, agent-infra/sandbox is a comprehensive platform that simplifies the development, testing, and deployment of AI agents by combining multiple tools and MCP services in one cohesive sandbox environment.
https://github.com/agent-infra/sandbox
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.
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.