Document AI / OCR
Part of AI & Machine Learning
Document processing, OCR, and structured data extraction
Services(5)
Ownership Structure
Deployment
License Type
Country
50%
Self-HostableApache-2.0
Document AI / OCR
Tesseract OCR
Open-source OCR engine supporting over 100 languages
★ 73.9k
50%
FoundationSelf-HostableMIT
Document AI / OCR
Docling
Open-source document parser for PDFs and images to Markdown and JSON
★ 59.3k
50%
BootstrappedSelf-HostableGPL-3.0
Document AI / OCR
Surya OCR
Open source document OCR with layout and table analysis
★ 19.7k
50%
Public (US)Self-HostableApache-2.0
Document AI / OCR
PaddleOCR
Open-source OCR toolkit for text detection and recognition in 100+ languages
★ 77.2k
35%
EU
Mixed (>30% Non-EU)
Document AI / OCR
Mistral OCR 3
Document processing model for text, tables, and handwriting extraction