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
Camofox-browser is an anti-detection headless browser server tailored for AI agents, built upon the Camoufox Firefox fork. It provides advanced fingerprint spoofing at the C++ implementation level, camouflaging parameters like `navigator.hardwareConcurrency`, WebGL renderers, AudioContext, screen geometry, and WebRTC, effectively bypassing common bot detection mechanisms, including Google and Cloudflare. This project wraps the Camoufox engine in a REST API, optimizing it for agent-based interactions by providing accessibility snapshots (which are significantly smaller than raw HTML), stable element references for reliable interaction, and search macros for popular websites. Key features include C++ anti-detection, element references for robust automation, token-efficient operation through accessibility snapshots, and session isolation. It supports cookie import, proxy integration with GeoIP, and structured logging. The browser is designed for low resource consumption, enabling deployment on minimal hardware like a Raspberry Pi or a $5 VPS, as it employs lazy browser launch and idle shutdown. Additional functionalities include YouTube transcript extraction, snapshot screenshots, large page handling with pagination, download capture, and DOM image extraction. It offers flexible deployment options (Docker, Fly.io, Railway), VNC interactive login, comprehensive OpenAPI documentation, and structured extraction with JSON Schema support. The project also includes optional session tracing and anonymized crash/hang telemetry to identify failure patterns without exposing sensitive data.
https://github.com/jo-inc/camofox-browser
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.
Stagehand is a production-ready AI web browsing framework that combines code and natural language to enable reliable and extensible browser automation.
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.