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
vdutts7/gpt4V-scraper
The GPT-4V Web Agent project is an advanced AI-powered tool designed to interact with web browsers by seeing, controlling, navigating, and performing tasks autonomously. It leverages the capabilities of GPT-4V, an AI model with vision, to automate web scraping, capture full-page screenshots, and extract meaningful information from web content. The project uses Puppeteer, a Node.js library, enhanced with a stealth plugin to bypass anti-bot detection mechanisms, ensuring smooth and undetected web automation. Users can customize timeout settings to optimize scraping efficiency. The project is structured in multiple parts: First, it captures screenshots of web pages, supporting authenticated sessions for sites requiring login, such as LinkedIn or Instagram. It supports Chrome or Chrome Canary browsers across MacOS, Windows, and Linux, with detailed configuration instructions for user data directories and executable paths. Second, it converts images to text using a Python environment with OCR-like capabilities, but enhanced by GPT-4V's understanding, allowing extraction of specific information based on user prompts. Third, it offers an "AutoGPT" style interactive chat interface where users can query the AI agent in real-time, guiding it to browse and extract data from the web, demonstrated with examples like retrieving trending cryptocurrency data from CoinMarketCap. The project is well-documented with setup instructions, environment configuration, and usage examples. It also includes a promotional offer for free cloud credits to deploy the tool. The AI agent's ability to see and interpret web content visually, combined with its control over browser navigation, makes it a powerful assistant for automated web tasks, research, and data extraction. This tool is particularly useful for developers, researchers, and data analysts looking to automate complex web interactions and data gathering with AI assistance.
https://github.com/vdutts7/gpt4V-scraper
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.
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.