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
citrolabs/ego-lite
ego lite is an innovative browser tailored for AI agents, enabling them to execute web automation tasks simultaneously with a human user without interference. It provides dedicated "Spaces" for each AI agent or task, ensuring isolation from the user's active tabs. This unique architecture allows multiple AI agents to multitask in parallel, completing complex operations significantly faster and with fewer tokens compared to conventional CLI-based browser automation tools. The project highlights several key features: a code-base rather than CLI-base approach for faster and more efficient task execution, resulting in higher success rates for complex workflows. It offers a strong page snapshot mechanism, leveraging kernel-level customization to provide high-quality visual data to AI models, even for challenging elements like deeply nested iframes. The `ego-browser` skill acts as an intermediary layer, allowing any AI agent (like Claude Code or Codex) to drive ego lite by writing JavaScript snippets that utilize its in-page tools (snapshot, fill, click, wait, navigate, capture). Additionally, ego lite is designed to integrate seamlessly with existing browser data by migrating Chrome profiles, ensuring agents inherit logins, cookies, and extensions without extra setup. It runs locally, keeping browsing data private, and is currently available on macOS with plans for Windows and Linux.
https://github.com/citrolabs/ego-lite
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.
jo-inc/camofox-browser
Camofox-browser is a stealth headless browser server, powered by Camoufox (a Firefox fork), designed for AI agents to bypass bot detection and Cloudflare, offering a Puppeteer/Playwright alternative.
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.