Explore Projects

Discover 352 open source projects

Active filters (1):

Search: pdf×

Clear all

Showing 1-20 of 352 projects

justjavac/free-programming-books-zh_CN

免费的编程中文书籍索引，支持多语言和主题

116.4K

Archived

Books & Guides

#books#programming#free

microsoft/markitdown

Converts files and office documents to Markdown for LLMs

90.2K

Stable

Python

MCP Servers

CLI Tools

Python

#markdown-converter#document-conversion#llm-input-preparation

fighting41love/funNLP

Comprehensive Chinese NLP resource collection for developers

79.2K

Archived

Python

LLM Frameworks

RAG & Vector

Python

#nlp#chinese-nlp#ai-resources

Stirling-Tools/Stirling-PDF

Open-source PDF platform for editing, converting, and automating PDFs with desktop, browser, and self-hosted options.

75.0K

Active

TypeScript

CLI Tools

General Utilities

TypeScript

#pdf-editor#pdf-converter#pdf-tools

PaddlePaddle/PaddleOCR

PaddleOCR converts documents/images to structured data for AI apps

71.6K

Active

Python

Computer Vision

MCP Servers

PaddlePaddle

#ocr#document-parsing#ai4science

opendatalab/MinerU

Converts complex documents into LLM-ready formats for agentic workflows

55.5K

Active

Python

Agents & Orchestration

Agent Coordination

Python

#document-analysis#pdf-extraction#llm-workflows

docling-project/docling

Converts documents to AI-ready formats with advanced parsing

55.0K

Active

Python

Computer Vision

CLI Tools

#document-parsing#pdf-converter#ocr

mozilla/pdf.js

JavaScript PDF viewer for web

52.9K

Active

JavaScript

Component Libraries (React)

Frontend Frameworks

JavaScript

#pdf-viewer#javascript#mozilla

hiroi-sora/Umi-OCR

Offline OCR software with batch processing, PDF support, and multi-language recognition.

42.4K

Stable

Python

CLI Tools

Computer Vision

Python

#ocr#python#paddleocr

siyuan-note/siyuan

Privacy-first, self-hosted knowledge management with markdown and AI integrations

41.7K

Active

TypeScript

Full-Stack Frameworks

RAG & Vector

Electron

#knowledge-base#markdown#local-first

paperless-ngx/paperless-ngx

Document management system for scanning, indexing, and archiving documents

37.1K

Active

Python

Collaboration & Real-time

Documentation

Django

#document-management#ocr#machine-learning

ocrmypdf/OCRmyPDF

Adds OCR text layer to scanned PDFs for searchability

32.8K

Active

Python

CLI Tools

Computer Vision

#ocr#pdf-processing#command-line

datalab-to/marker

Converts PDFs to markdown and JSON with high accuracy

32.2K

Active

Python

Computer Vision

CLI Tools

#pdf-to-markdown#document-processing#ai-ocr

PDFMathTranslate/PDFMathTranslate

AI-powered PDF translation preserving formats and math for scientific documents

32.0K

Stable

Python

MCP Servers

LLM Wrappers & SDKs

#pdf-translation#ai-translation#scientific-papers

parallax/jsPDF

Client-side PDF generation library for JavaScript

31.2K

Active

JavaScript

HTTP Clients

#pdf-generation#javascript#client-side

hehonghui/awesome-english-ebooks

英语电子书下载资源合集，包含经济学人、纽约客等杂志的epub、mobi、pdf格式下载

29.4K

Active

CSS

Awesome Lists

#ebooks#english-magazines#pdf

posquit0/Awesome-CV

LaTeX template for creating professional CVs, resumes, and cover letters

26.9K

Active

TeX

Documentation

#latex#cv-template#resume

forthespada/CS-Books

A collection of over 1000 computer science books and resources for learning and interviews.

26.4K

Stable

Books & Guides

Awesome Lists

#cs-books#algorithms#c

koodo-reader/koodo-reader

A cross-platform ebook reader with sync and backup capabilities

26.2K

Active

JavaScript

Cross-Platform

JavaScript

#ebook-reader#cross-platform#sync

koreader/koreader

Ebook reader for e-ink and mobile devices

25.6K

Active

Lua

Cross-Platform

General Utilities

#ebook-reader#lua#eink

2...18

Stay in the loop

Get weekly updates on trending AI coding tools and projects.