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
jo-inc/camofox-browser
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
Also in Browser Automation Tools
CloakHQ/CloakBrowser
CloakBrowser provides a stealthy Chromium binary with C++ source-level fingerprint patches to pass bot detection, serving as a drop-in Playwright/Puppeteer replacement.
jackwener/OpenCLI
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.
browserbase/stagehand
Stagehand is a production-ready AI web browsing framework that combines code and natural language to enable reliable and extensible browser automation.
browser-use/web-ui
A web-based user interface, powered by Gradio, for interacting with browser automation agents, supporting various LLMs and custom browser configurations.
citrolabs/ego-lite
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.
microsoft/fara
Fara-7B is a compact and efficient agentic small language model by Microsoft designed to perform multi-step computer tasks through visual interaction, achieving state-of-the-art performance on web automation benchmarks while enabling on-device deployment for privacy and low latency.
oxylabs/ai-crawler-py
AI-Crawler by Oxylabs AI Studio is an AI-powered web crawling tool that extracts relevant data from websites using natural language prompts and outputs structured JSON or Markdown formats for easy integration.