PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Recent spike this week

7d +0.38% +345 stars in 7d
30d Not tracked yet — first tracked 2026-09-02
90d Not tracked yet — first tracked 2026-09-02
Sep 2, 2026: 88,703 starsSep 3, 2026: 88,771 starsSep 5, 2026: 88,906 starsSep 6, 2026: 88,949 starsSep 7, 2026: 89,014 starsSep 8, 2026: 89,097 starsSep 9, 2026: 89,179 starsSep 10, 2026: 89,256 starsSep 11, 2026: 89,323 starsSep 12, 2026: 89,372 starsSep 13, 2026: 89,418 starsSep 14, 2026: 89,493 starsSep 15, 2026: 89,575 starsSep 16, 2026: 89,640 starsSep 17, 2026: 89,702 starsSep 18, 2026: 89,765 starsSep 19, 2026: 89,818 starsSep 20, 2026: 89,865 starsSep 21, 2026: 89,928 starsSep 22, 2026: 89,994 starsSep 23, 2026: 90,068 starsSep 24, 2026: 90,141 starsSep 25, 2026: 90,197 starsSep 26, 2026: 90,230 starsSep 27, 2026: 90,268 starsSep 28, 2026: 90,333 starsSep 29, 2026: 90,404 starsSep 30, 2026: 90,452 starsOct 1, 2026: 90,486 stars 88,70389,59590,486 Sep 2Oct 1

88,703 → 90,486 stars since Sep 2

88,590 Stars 11,429 Forks 250 Open issues
View on GitHub ↗ Visit site ↗
ai4sciencechineseocrdocument-parsingdocument-translationkieocrpaddleocr-vlpdf-extractor-ragpdf-parserpdf2markdownpp-ocrpp-structurerag