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
zabirauf/AutoGPT.js
AutoGPT.js is an innovative open-source project designed to bring the advanced functionalities of AutoGPT directly to web browsers, enhancing accessibility and privacy for users. By running entirely in the browser environment, it eliminates the need for server-side processing, allowing users to interact with GPT agents locally. The project leverages modern web technologies such as the Web File System Access APIs to enable users to create and read files from their local computers, facilitating seamless integration with local data. AutoGPT.js supports the creation and execution of multiple GPT agents, enabling complex workflows and automation tasks. It also features code generation capabilities and short-term memory to maintain context during interactions. For information retrieval, it integrates DuckDuckGo search, currently implemented through a server proxy to fetch search results. Additionally, it supports stateless URL visits, also proxied through a server, to access web content. The project roadmap includes plans to incorporate LangChain for a more extensible architecture, advanced configuration settings for AutoGPT parameters like temperature and prompts, and sandboxed JavaScript code execution within iframes for enhanced security. Future enhancements also aim to support multiple large language model APIs such as Bard and Cohere, and integrate web-based LLMs like WebLLM and LLaMa, although performance considerations are noted. The user experience is set to improve with features like tabbed interfaces to display accessed or created files. Development is straightforward, with environment setup, dependency installation, and a development server launch process clearly documented. Deployment options are versatile, including Fly.io, Docker, and direct server hosting with reverse proxy configurations. The project encourages community contributions and is licensed under the MIT License, promoting open collaboration and innovation in browser-based AI agent technology.
https://github.com/zabirauf/AutoGPT.js
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.