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
reidbarber/webmarker
WebMarker is a tool designed to visually mark interactive elements on web pages to facilitate their use with vision-language models such as GPT-4o, Claude 3.5, and Google Gemini 1.5. It enhances the visual grounding capabilities of these models by adding clear, labeled visual markers and bounding boxes to elements like links, buttons, inputs, and other interactive components on a webpage. This marking process allows vision-language models to better understand and interact with web page elements by referencing these labels in prompts. The core functionality involves calling a `mark()` function that identifies and marks interactive elements on the page. This function returns an object mapping labels to the marked elements, including the element itself, the label element, and the bounding box element. Users can then take a screenshot of the marked page and send it along with a prompt to a vision-language model, instructing it to perform actions such as clicking or hovering on labeled elements. WebMarker supports customization through various options, including specifying which elements to mark via CSS selectors, customizing label generation, styling the labels and bounding boxes, and controlling the placement of marks relative to elements. It also allows marking only elements visible in the current viewport and supports marking within a specific container element. The project includes integration examples with Playwright, demonstrating how to inject the WebMarker library into a page, mark elements, interact with them programmatically, and optionally check or remove markings. This makes it suitable for automated testing, web scraping, or building intelligent agents that interact with web content based on vision-language model outputs. Overall, WebMarker is a powerful utility for bridging web page content with advanced vision-language models, enabling more effective and interactive web automation and analysis workflows.
https://github.com/reidbarber/webmarker
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.