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
ishan0102/vimGPT
vimGPT is an innovative project that explores the use of multimodal large language models (LLMs), specifically GPT-4V, to enable web browsing through vision capabilities combined with keyboard navigation. The project integrates GPT-4V's vision features with Vimium, a popular Chrome extension that allows users to navigate web pages using only the keyboard. This combination provides a unique interface where the AI model can interact with web content visually and perform actions by leveraging Vimium's keyboard shortcuts, overcoming the challenge of interpreting web page elements without direct access to the browser's DOM as text. The project is designed to run with Python and requires setting up Vimium locally to be loaded manually during browser automation with Playwright. It supports a voice mode where users can issue voice commands to control the browser, making the interaction more natural and accessible. This voice mode allows users to state their objectives verbally, and vimGPT executes the corresponding actions in real-time. vimGPT is not only a proof of concept but also a platform for experimentation and collaboration. The developer suggests numerous future enhancements, such as integrating the upcoming Assistant API for better context management, creating specialized Vimium forks for improved element overlay and interaction, using higher resolution images to improve model accuracy, and fine-tuning other multimodal models like LLaVa or CogVLM for efficiency. Additional ideas include adding speech-to-text capabilities, enabling the tool to work with users' own browsers, incorporating accessibility features for visually impaired users, and developing mechanisms to avoid repetitive actions. The project also references related research and tools, highlighting its foundation in current AI and web navigation advancements. Overall, vimGPT represents a cutting-edge approach to AI-assisted web browsing, combining vision-based AI models with keyboard-driven navigation to create a versatile and accessible browsing experience.
https://github.com/ishan0102/vimGPT
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.
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.
TaxyAI/browser-extension
Taxy AI is an open-source Chrome extension that uses GPT-4 to automate repetitive browser tasks by interpreting natural language instructions and interacting with web pages through an action cycle.