Read Website Fast

•
163
•

Extracts web content quickly and converts it to clean, token-efficient Markdown for AI agents and LLM pipelines.

Addresses the limitations of traditional web crawlers by offering a fast and token-efficient solution for AI agents. This tool fetches web pages locally, strips noise, and converts content to clean Markdown while preserving links, ensuring minimal token footprint and efficient processing for LLM pipelines and IDEs like Claude Code.

主な機能

01Converts HTML to clean Markdown using Mozilla Readability and Turndown GFM
02Link preservation for knowledge graphs and optional chunking for downstream processing
03Fast, token-efficient content extraction optimized for AI agents
04Configurable concurrent fetching and depth crawling for comprehensive data collection
05Smart caching with SHA-256 hashed URLs and polite crawling with robots.txt support
061 GitHub stars

ユースケース

01Powering AI agents with structured and clean web content
02Integrating clean web data into LLM pipelines and IDEs for context and research
03Efficient web scraping for data collection and analysis