AgentQL is a suite of tools for connecting your AI to the web. Featuring a query language and Playwright integrations for interacting with elements and extracting data quickly, precisely, and at scale. Includes REST API, Python and JavaScript SDKs, browser debugger.

🌎💪 BrowserGym, a Gym environment for web task automation

Tools to build web AI agents that can authenticate, interact with and extract data from any website.

MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

[NeurIPS'25 D&B] Mind2Web-2 Benchmark: Evaluating Agentic Search with Agent-as-a-Judge

🌟Official code of our AAAI26 paper 🔍WebFilter

AgentQL's integrations with workflow automation tools and AI agent frameworks let you extract structured data from web pages using queries or natural language and interact with the web with Playwright. Resilient, fast, and AI-ready.

🚀 Fast AI web browser agent to automate repetitive tasks

An AI-powered Web Agent Chrome Extension. Features cross-site task persistence, background proxy for CSP bypass, and physical interaction modes. Optimized for private/intranet deployments. (一个基于 AI 的网页智能助手插件。支持跨站任务续传、绕过 CSP 的后台代理、以及物理级交互模式。专为私有化/内网环境优化。)

WebAgent is an AI-driven full-stack application that generates responsive websites from simple text prompts or uploaded design mockups. Built with a FastAPI backend and a React frontend, it uses advanced AI models to translate user intent or layout into real-time HTML/CSS/JS websites.

WebAgent for Information Seeking