The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

Browser4: a lightning-fast, coroutine-safe browser for your AI.

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).

Open‑source alternative to Perplexity Comet and director.ai and firecrawl combined

Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 全自动网页评估测试 Agent，一键完成性能、功能与交互体验的测试评估

✉️ Use the power of browser-use to contact any person or organization... by any means necessary

Auto-Browse: AI Enabled Browser Automation

Build your own AI operators like OpenAI

A smart AI agent that controls your browser with natural language, using Playwright, LangChain, and advanced LLMs to navigate, analyze, and perform tasks.

User-Agent information harvester

The Anal-Queen of AI Browser Automation 🏴‍☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.

Screen recording and computer interaction capture tool that records keyboard/mouse input, screen video, DOM snapshots, and accessibility trees. Perfect for creating datasets to train and evaluate computer-use AI models.

An AI-powered browser automation tool built with Next.js and Gemini 2.0 Vision AI. Transform natural language into browser automation with visual understanding.

Serverless AI browser agent

Antibot Browser Agent

can we massively automate and collect environments and trajectories of browser tasks?

Perplexity Comet Alternative. Chrome extension for browser automation, multi-tab chat, video analysis, and more. Powered by @dom-engine

Agent-CE is a containerized continuous evaluation (CE) platform for web browsing agents. It provides production-ready Docker images and CI/CD pipelines for running and evaluating multiple agent frameworks including Browser Use, Notte, Anthropic Computer Use, and OpenAI Computer Use.

A simple browser agent that transforms unstructured course content from any MOOC website into clean, structured data.

Screen recording and computer interaction capture tool that records keyboard/mouse input, screen video, DOM snapshots, and accessibility trees. Perfect for creating datasets to train and evaluate computer-use AI models.