browser-use/browser-use
Browser-use is a project that enables AI agents to control and automate web browsers, allowing users to perform complex tasks through natural language commands and AI-driven browser interactions.
Awesome AI Agents › Browser Automation Tools
Stagehand is a production-ready AI web browsing framework designed to simplify and extend browser automation. It addresses the limitations of existing tools like Selenium, Playwright, and Puppeteer by allowing developers to choose when to write code and when to use natural language for browser interactions. This hybrid approach enables more predictable and efficient automation in production environments. The framework integrates state-of-the-art computer use models from providers like OpenAI and Anthropic with minimal code, enhancing the capability to navigate and interact with web pages intelligently. Key features include the ability to preview and cache AI-driven actions before execution, which helps optimize performance and reduce costs by saving tokens. Stagehand leverages Playwright as its backbone for resilient web automation, ensuring reliability and speed. The framework supports executing individual actions, larger agent-driven tasks, and data extraction from web pages using structured schemas. The project provides comprehensive documentation and a quickstart guide to help users get started easily. It also encourages community contributions and offers support through a dedicated Slack channel. The source code is open-source under the MIT License, and the project emphasizes improving reliability, speed, and cost efficiency in that order. Stagehand is ideal for developers looking to build sophisticated browser automation workflows that combine the precision of code with the flexibility of AI-driven natural language commands. It is suitable for tasks such as navigating complex web interfaces, extracting data, and automating repetitive browsing activities with enhanced intelligence and control.
https://github.com/browserbase/stagehand
Browser-use is a project that enables AI agents to control and automate web browsers, allowing users to perform complex tasks through natural language commands and AI-driven browser interactions.
Open-source Python web crawler and scraper that converts web pages into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an API and an MCP server.
CloakBrowser provides a stealthy Chromium binary with C++ source-level fingerprint patches to pass bot detection, serving as a drop-in Playwright/Puppeteer replacement.
dots is an open-source CLI/web agent pairing any OpenRouter model with a patched Firefox engine for undetectable, human-like browsing, with per-seed identities and persistent login profiles.
OpenCLI converts any website or local tool into a command-line interface, enabling both human interaction and AI agent automation through logged-in browser sessions.
Rust headless browser built for AI agents, with on-demand layout and rendering plus a CLI and CDP/WebDriver Classic/BiDi servers for lightweight page fetching and browser-use workloads.
ego lite is a specialized browser designed for AI agents to perform web automation in parallel with human browsing, offering isolated workspaces and enhanced page snapshots.
A web-based user interface, powered by Gradio, for interacting with browser automation agents, supporting various LLMs and custom browser configurations.