#1
A Repo For Document AI
3.2K starsJun 12, 2026 pushdocument-processingPythonOCR
$ npx skills add deepdoctection/deepdoctectionAlternatives
Unilm alternatives for AI agents.
Compare similar skills by workflow fit, trust score, quality, GitHub adoption, maintenance, and install readiness.
Current skill
Unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
100
Quality
100
Trust
22K
Stars
#2
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
1.9K starsJun 7, 2026 pushdocument-processingPythonPDF
$ npx skills add wxyhgk/retain-pdf#3
Python tool for converting files and office documents to Markdown.
152K starsMay 26, 2026 pushdocument-processingPythonPDF
$ npx skills add microsoft/markitdown#4
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
67K starsJun 11, 2026 pushdocument-processingPythonPDF
$ npx skills add opendatalab/MinerU#5
Get your documents ready for gen AI
61K starsJun 12, 2026 pushdocument-processingPythonPDF
$ npx skills add docling-project/docling#6
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
45K starsNov 20, 2025 pushdocument-processingPythonOCR
$ npx skills add hiroi-sora/Umi-OCR#7
A community-supported supercharged document management system: scan, index and archive all your documents
42K starsJun 13, 2026 pushdocument-processingPythonPDF
$ npx skills add paperless-ngx/paperless-ngx#8
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/OCRmyPDF#9
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#10
OCR model that handles complex tables, forms, handwriting with full layout.
11K starsApr 22, 2026 pushdocument-processingPythonOCR
$ npx skills add datalab-to/chandra#11
A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files
10K starsJun 11, 2026 pushdocument-processingPythonPDF
$ npx skills add py-pdf/pypdf#12
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
10K starsMay 24, 2026 pushdocument-processingPythonOCR
$ npx skills add zyddnys/manga-image-translator#13
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
10.0K starsJun 11, 2026 pushdocument-processingPythonPDF
$ npx skills add pymupdf/PyMuPDF#14
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
9.0K starsMar 25, 2026 pushdocument-processingPythonPDF
$ npx skills add bytedance/Dolphin#15
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
9.0K starsApr 9, 2026 pushdocument-processingPythonOCR
$ npx skills add YaoFANGUK/video-subtitle-extractor#16
GLM-OCR: Accurate × Fast × Comprehensive
6.9K starsApr 21, 2026 pushdocument-processingPythonOCR
$ npx skills add zai-org/GLM-OCRHow 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 Unilm 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.