Trending repositories

Ranked by Attention Score: stars gained over the last 180 complete days

Period

Sort order

Tag

Filters

Apply

Filters

Primary language

License

Total stars

Last push

Created

Archived

Clear all filters

24 repositories by Attention Score · May 8, 2026 – Nov 3, 2026 (UTC)

Tag: OCR

1.opendatalab / MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

extract-data
layout-analysis
ocr
parser
pdf
pdf-converter
+10 more

Python Other license83K total6.9K forks

+21,536 stars

from 61,528 · score 9.98

2.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.

ocr
chineseocr
pdf2markdown
pp-ocr
pp-structure
document-parsing
+7 more

Python APACHE-2.092K total12K forks

+15,589 stars

from 76,624 · score 9.65

TranslatedOCR software, free and offline. Open-source, free offline OCR software. Supports screenshots/batch importing of images, PDF document recognition, excluding watermarks/headers and footers, and scanning/generating QR codes. Has built-in multi-language libraries.

paddleocr
ocr
ocr-python
umi-ocr
qml
qt
+1 more

Python MIT48K total4.7K forks

+4,924 stars

from 43,479 · score 8.50

4.tesseract-ocr / tesseract

Tesseract Open Source OCR Engine (main repository)

tesseract
tesseract-ocr
ocr
lstm
machine-learning
ocr-engine
+1 more

C++APACHE-2.077K total11K forks

+3,803 stars

from 73,521 · score 8.24

5.HIllya51 / LunaTranslator

TranslatedVisual Novel Translator

galgame
visual-novel
translator
reverse-engineering
ocr

C++GPL-3.014K total1.2K forks

+2,740 stars

from 11,272 · score 7.92

6.allenai / olmocr

Toolkit for linearizing PDFs for LLM datasets/training

Python APACHE-2.020K total1.7K forks

+2,683 stars

from 17,130 · score 7.90

7.datalab-to / chandra

OCR model that handles complex tables, forms, handwriting with full layout.

Python APACHE-2.013K total1.3K forks

+2,332 stars

from 10,345 · score 7.75

8.datalab-to / surya

OCR, layout analysis, reading order, table recognition in 90+ languages

Python APACHE-2.022K total1.6K forks

+2,002 stars

from 19,576 · score 7.60

9.ocrmypdf / OCRmyPDF

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

python
ocr
pdf
image-processing
tesseract

Python MPL-2.035K total2.4K forks

+1,950 stars

from 33,279 · score 7.58

10.STranslate / STranslate

TranslatedA ready-to-go translation ocr tool developed with WPF. A ready-to-use translation and OCR tool developed with WPF

wpf
ocr
plugin
translate
stranslate

C#MIT8.5K total452 forks

+1,873 stars

from 6,638 · score 7.54

11.pot-app / pot-desktopArchived

Translated🌈 A cross-platform software for text translation and recognition.

translation
pot
tauri
translate
pot-app
ocr
+5 more

JavaScript GPL-3.019K total1.1K forks

+1,826 stars

from 17,516 · score 7.51

12.deepseek-ai / DeepSeek-OCR

Contexts Optical Compression

Python MIT24K total2.2K forks

+1,360 stars

from 22,758 · score 7.22

13.sml2h3 / ddddocr

TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version

ocr
ddddocr
captcha

Python MIT15K total2.4K forks

+995 stars

from 13,905 · score 6.90

14.naptha / tesseract.js

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

tesseract
webassembly
ocr
javascript
deep-learning

JavaScript APACHE-2.039K total2.4K forks

+897 stars

from 37,913 · score 6.80

15.JaidedAI / EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

ocr
deep-learning
crnn
pytorch
lstm
machine-learning
+9 more

Python APACHE-2.030K total3.6K forks

+893 stars

from 29,228 · score 6.80

16.zyddnys / manga-image-translator

TranslatedTranslate manga/image: one-click translation of text in all kinds of images https://cotrans.touhou.ai/ (no longer working)

manga
anime
ocr
deep-learning
image-processing
auto-translation
+9 more

Python GPL-3.011K total1.1K forks

+834 stars

from 9,736 · score 6.73

17.lukas-blecher / LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

machine-learning
transformer
im2latex
deep-learning
image2text
latex
+11 more

Python MIT17K total1.3K forks

+397 stars

from 16,207 · score 5.99

18.facebookresearch / nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

Python MIT10K total633 forks

+212 stars

from 9,883 · score 5.36

19.DayBreak-u / chineseocr_lite

TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M

ncnn
ocr
pytorch

C++GPL-2.012K total2.3K forks

+133 stars

from 12,223 · score 4.90

20.getomni-ai / zerox

OCR & Document Extraction using vision models

TypeScript MIT12K total840 forks

+130 stars

from 12,123 · score 4.88

21.openalpr / openalpr

Automatic License Plate Recognition library

C++AGPL-3.011K total2.5K forks

+113 stars

from 11,364 · score 4.74

22.vipstone / faceai

TranslatedAn entry-level project for face, video, and text detection and recognition.

dlib
opencv
tesseract-ocr
keras
tensorflow

Python MIT11K total2.5K forks

+79 stars

from 11,017 · score 4.38

23.the-paperless-project / paperlessArchived

Scan, index, and archive all of your paper documents

documents
paper
ocr
archiving
search

Python GPL-3.07.9K total496 forks

+29 stars

from 7,883 · score 3.40

24.NMAC427 / SwiftOCR

Fast and simple OCR library written in Swift

ocr
swift
ocr-library
optical-character-recognition
ocr-engine
ios
+3 more

Swift APACHE-2.04.6K total474 forks

+12 stars

from 4,616 · score 2.56

Order: Attention Score

Most net stars gained in the window first. The score only puts this gain on a log scale, so the order is the order of the gain.

How the ranking works

Ranked by stars gained in the window. The score is the natural log of one plus that gain, so a repository's rank is exactly its star gain's rank.

score = log1p(net stars gained in the trailing T complete UTC days)

A repository is ranked only when its Star History covers every day of the window and its latest Observation is not missing.

The longest window is 180 days. Star History from the Repository Host goes back at most 180 days before the first daily record that AwesomeRepos made for the repository. A longer window needs more of these daily records first. A repository younger than the window does not rank in it.

The filters select from the same eligible repositories. A repository matches the topics when it has any of them. Total stars is the count now. Last push and creation on the Repository Host count back from the start of today (UTC). The counts beside the languages, licenses, and topics include all ranked repositories in the window. A Tag holds the repositories that have it. See Tags.

Repositories enter the index from the starting dataset of the index, or by gaining stars faster than the published admission threshold, whatever their size. A repository stays in the index after it enters. Thus an archived repository can still rank.

Browse the Repository Index