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.
69,362 stars
Last commit Dec 8, 2025agpl-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.
46,170 stars
Last commit Dec 8, 2025mit