46 AI tools for Browser & OS automation
Puppeteer automation skill that provides production-ready browser automation patterns for web scraping, end-to-end testing, and dynamic content handling with
A wrapper around the Playwright library that allows navigation to websites, extraction of text and hyperlinks, and interaction with page elements using async
Async Base Browser is a CAMEL-AI toolkit that provides asynchronous browser automation capabilities for AI assistants to interact with web pages concurrently.
Base Browser is a CAMEL-AI toolkit component that provides browser automation capabilities for AI assistants to interact with web pages programmatically.
DOMRectangle is a CAMEL-AI toolkit component that defines rectangular boundary coordinates for DOM elements in browser automation workflows.
Screenshot Toolkit is a reusable skill that enables AI assistants to capture screenshots programmatically for documentation, testing, and visual monitoring
TypeScript SDK for running Playwright tests at scale on Azure-hosted browsers with integrated portal reporting and Microsoft Entra ID authentication.
.NET SDK for provisioning and managing Microsoft Playwright Testing workspaces via Azure Resource Manager-create workspaces, check quotas, and configure
Browser automation skill covering Playwright and Puppeteer for web testing, scraping, and AI agent interactions with user-facing locators, auto-wait
MCP server providing serverless cloud infrastructure for AI agents through Alibaba Cloud Wuying AgentBay, with browser automation, file operations, and
Browserbase MCP server for LLMs to automate cloud browser tasks, extract data, and take screenshots.
Official Chrome DevTools MCP server that gives AI assistants control over a live Chrome browser for automation, debugging, performance tracing, and network
MCP server providing computer control capabilities like mouse, keyboard, and OCR.
MCP server that gives Claude AI models control of your computer through keyboard and mouse automation, enabling desktop background changes, app control, and UI
Open-source MCP server that enables AI to control remote macOS systems via screen sharing, providing screenshot capture, keyboard input, mouse control, and
Puppeteer MCP enables AI-powered browser automation for navigation, screenshots, form interaction, and content extraction.
PlaywrightMCPToolkit is an MCP server connector that provides an interface for interacting with web browsers using the Playwright automation library through
BrowserLoop MCP server captures screenshots and console logs from web pages using Playwright for AI development.
Browser automation example demonstrating web application testing using Playwright in a headless environment for automated quality assurance workflows.
A cookbook demonstrating how to connect OpenAI's Agents SDK Computer Use tool to Daytona sandboxes, enabling agents to see and control a Linux desktop with