Tags: #web-scraping

An API for AI agents to reliably search, scrape, and interact with the web, providing clean, LLM-ready data at scale.

An adaptive Python web scraping framework designed to handle everything from single requests to large-scale crawls, featuring anti-bot bypass and intelligent parsing.

An AI browser automation framework that combines natural language and code for flexible, reliable, and maintainable web control.

Enables AI agents to interact with and automate tasks on websites, making web content accessible for large language models.

A TypeScript library that leverages Large Language Models to extract structured data from any webpage.

A Python library that leverages LLMs and graph logic to simplify web scraping and data extraction from various sources.

A highly efficient command-line tool to download, resize, and package large sets of image URLs into machine learning datasets.

A fast native Rust CLI for browser automation, specifically designed for AI agents.

CloakBrowser is a stealth Chromium browser engineered with C++ source-level fingerprint patches to bypass advanced bot detection, serving as a drop-in replacement for Playwright and Puppeteer.