The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
7 daysStars9.6k24h gain+6Score2.6
Find trending repositories by name or description.
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
Parse and understand source code in 300+ languages from every major language, with one dependency and no grammars to compile.
Turn messy, real-world HTML into clean Markdown, from every major language.
Turn any website into clean, structured data: Markdown, metadata and links from one page or a whole site, in every major language.