#1
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
34K starsJun 12, 2026 pushdocument-processingPythonPDF
$ npx skills add ocrmypdf/OCRmyPDFAlternatives
Donut alternatives for AI agents.
Compare similar skills by workflow fit, trust score, quality, GitHub adoption, maintenance, and install readiness.
Current skill
Donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
79
Quality
88
Trust
6.9K
Stars
#2
带带弟弟 通用验证码识别OCR pypi版
14K starsMar 10, 2026 pushdocument-processingPythonOCR
$ npx skills add sml2h3/ddddocr#3
OCR model that handles complex tables, forms, handwriting with full layout.
11K starsApr 22, 2026 pushdocument-processingPythonOCR
$ npx skills add datalab-to/chandra#4
PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
5.8K starsJun 6, 2026 pushdocument-processingPythonPDF
$ npx skills add oomol-lab/pdf-craft#5
GLM-OCR: Accurate × Fast × Comprehensive
7.0K starsApr 21, 2026 pushdocument-processingPythonOCR
$ npx skills add zai-org/GLM-OCR#6
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
1.6K starsApr 24, 2025 pushdocument-processingPythonOCR
$ npx skills add RQLuo/MixTeX-Latex-OCR#7
A Repo For Document AI
3.2K starsJun 12, 2026 pushdocument-processingPythonOCR
$ npx skills add deepdoctection/deepdoctection#8
Collection of open-source libraries and tools for Robotic Process Automation (RPA), designed to be used with both Robot Framework and Python
1.5K starsJun 14, 2026 pushdocument-processingPythonOCR
$ npx skills add robocorp/rpaframework#9
OCR powered screen-capture tool to capture information instead of images
2.6K starsMay 19, 2026 pushdocument-processingPythonOCR
$ npx skills add dynobo/normcap#10
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
1.5K starsJun 8, 2026 pushdocument-processingPythonOCR
$ npx skills add kotaro-kinoshita/yomitoku#11
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
2.9K starsMar 22, 2026 pushdocument-processingPythonOCR
$ npx skills add Dicklesworthstone/llm_aided_ocr#12
Handwritten Text Recognition (HTR) system implemented with TensorFlow.
2.2K starsJan 31, 2026 pushdocument-processingPythonOCR
$ npx skills add githubharald/SimpleHTR#13
Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)
366 starsOct 31, 2022 pushdocument-processingPythonDocument AI
$ npx skills add jpWang/LiLT#14
A Python wrapper for the tesseract-ocr API
2.2K starsMar 16, 2026 pushdocument-processingPythonOCR
$ npx skills add sirfz/tesserocr#15
[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
3.2K starsNov 9, 2025 pushdocument-processingPythonOCR
$ npx skills add kerlomz/captcha_trainer#16
在保留版面、公式与结构的前提下进行 PDF 翻译，适用于科研与技术文档
2.0K starsJun 18, 2026 pushdocument-processingPythonDocument AI
$ npx skills add wxyhgk/retain-pdfHow to choose
When should you switch?
Use an alternative when it has a clearer install path, higher trust score, fresher maintenance, or better platform fit for your current agent stack. Keep Donut if it already passes your workflow test and repository review.
Next step
Compare top candidates side by side
Open the compare page, test the install commands in a sandbox, and check each repository before using a skill in production.