firecrawl/firecrawl
Firecrawl is an advanced web data API that crawls and scrapes entire websites to convert content into clean, LLM-ready markdown or structured data for AI applications.
Awesome AI Agents › Web Automation Systems
TaxyAI/browser-extension
Taxy AI is an innovative browser extension designed to automate repetitive browser tasks using GPT-4, a powerful language model. The extension allows users to define ad-hoc instructions that the AI interprets to control the browser, performing actions such as clicking buttons, entering text, and navigating web pages. This automation aims to save users time and effort by handling routine tasks automatically. Currently in a research preview phase, Taxy AI is open-source and emphasizes privacy by not sending any page content or instructions to external servers. Users can run the extension locally by following installation instructions involving Node.js and loading the extension into Chrome. Once installed, the extension can be activated via a popup or a developer tools panel, requiring an OpenAI API key for operation. The core functionality revolves around an action cycle where the extension extracts and simplifies the webpage's DOM, sends it along with user instructions to the GPT-4 model, and executes the AI's recommended actions through the Chrome debugger API. This cycle repeats until the task is complete, an error occurs, or the user stops the process. Taxy AI supports a variety of use cases demonstrated through simple demos like protecting a GitHub branch, searching and playing movies on Netflix, creating calendar events, and writing essays in the OpenAI playground. The project is built using modern web technologies including React, TypeScript, and Webpack, and follows Chrome Extension Manifest V3 standards. It is designed for users who want to automate browser interactions without manual scripting, leveraging AI to interpret natural language commands and perform complex workflows. Future plans include adding features for saved and scheduled workflows to enhance usability for a broader audience.
https://github.com/TaxyAI/browser-extension
Also in Web Automation Systems
nanobrowser/nanobrowser
Nanobrowser is an open-source Chrome extension that enables AI-powered web automation through a multi-agent system using user-configured LLM API keys, offering a privacy-focused and cost-effective alternative to commercial tools like OpenAI Operator.
steel-dev/steel-browser
Steel Browser is an open-source browser API that enables developers to build AI-powered web agents and automation tools with full browser control, session management, proxy support, and debugging features, simplifying web automation without infrastructure overhead.
fake-useragent/fake-useragent
fake-useragent is a Python package that provides an up-to-date and customizable user-agent faker using a real-world database for realistic user-agent strings.
ishan0102/vimGPT
vimGPT is a project that combines GPT-4V's vision capabilities with the Vimium keyboard navigation extension to enable AI-assisted web browsing through visual and keyboard interactions.
brightdata/brightdata-mcp
Bright Data MCP is a powerful Model Context Protocol server that enables AI agents and applications to access and extract real-time web data seamlessly, bypassing geo-restrictions and bot protections for enhanced web scraping and navigation.
spider-rs/spider
A concurrency-first web crawler and scraper written in Rust that streams pages as they arrive and renders JavaScript only when needed, with bindings for Node.js and Python and an MCP server for agents.
nottelabs/notte
Notte is an open-source full stack framework that creates intelligent web browsing agents using a perception layer to enable fast, reliable, and cost-effective interactions with websites through large language models.