Data Extraction
Firecrawl
Firecrawl is a web scraping and crawling API that converts any website into clean, structured data ready for AI applications and automation workflows.
72,790 stars
Last commit Jan 3, 2026agpl-3.0
Docling
Docling is a comprehensive document processing platform that parses diverse formats with advanced PDF understanding and provides seamless integrations with generative AI ecosystems.
48,767 stars
Last commit Dec 24, 2025mit