PaddlePaddle /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.
ai4sciencechineseocrdocument-parsingdocument-translationkieocrpaddleocr-vlpdf-extractor-rag
Stars92,286
Forks11,619
Open issues260
Avg. stars / day39faster than 20% of Python
LanguagePython
LicenseApache-2.0
CreatedMay 8, 2020
Last activitySep 16, 2026
Momentum
starts with the second daily updateRepocharts records a data point every day. Growth figures appear from tomorrow on.
Stars over time
tracked daily since Nov 5, 202692,286 stars today. This graph fills in as daily data points come in.
Chart positions
November 5, 2026| Chart | Rank | Prev. | Peak | Days on chart | At this rank |
|---|---|---|---|---|---|
| Python | #41 · | – | #41 | 1 | 1 day |
Rank history
last 90 days, #1 at the topThe rank history appears after the second daily update.
Compared with the Python chart
bar = this repo, line = chart medianStars92.3k76% of median
Forks11.6k76% of median
Avg. stars per day3937% of median
Open issues26055% of median
Commit activity
170 commits in the last 52 weeksSimilar repositories
by shared topics, language and charts
Cite and share
According to Repocharts, PaddlePaddle/PaddleOCR ranks #41 in the Python ranking on November 5, 2026.