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
nat/natbot
Natbot is a project that enables driving a web browser using GPT-3, an advanced language model developed by OpenAI. The core idea is to leverage GPT-3's natural language understanding and generation capabilities to interact with and control browser actions programmatically. This can include navigating web pages, clicking buttons, filling out forms, and other browser automation tasks. The project aims to create a more intelligent and flexible browser automation tool that can understand complex instructions and perform tasks in a human-like manner. The repository includes a demo showcasing how GPT-3 can be used to control a browser, highlighting the potential of combining AI language models with web automation. The project is in an early stage and invites contributions and improvements. Some of the suggested enhancements include developing better prompts to improve GPT-3's performance, implementing prompt chaining to handle more complex sequences of actions, and creating a recorder to collect human feedback for improved few-shot learning. Additionally, there are plans to improve DOM serialization to better represent the web page structure and to enable the agent to use multiple browser tabs and switch between them seamlessly. Natbot represents an innovative approach to browser automation by integrating cutting-edge AI technology. It opens up possibilities for more intuitive and adaptive automation workflows that go beyond traditional scripting methods. By using GPT-3, the project aims to make browser control more accessible and powerful, potentially benefiting developers, testers, and users who need to automate web interactions. The project is open to community contributions, encouraging collaboration to enhance its capabilities and usability.
Also in Browser Automation Tools
unclecode/crawl4ai
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.
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.
feder-cr/dots
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.
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.
lexmount/moli
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.
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.