Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
19 projects
Remove filter #pdf7.3k
- 12.9k
LiteParse
Local PDF and office document parser with OCR and bounding boxes
- 12.5k
Chandra OCR
OCR model converting scanned pages and PDFs into layout-aware Markdown
- Giorgio Garofalo16.3k
Quarkdown
Markdown-based typesetting with functions for papers, slides, and sites
- 18.8k
DocuSeal
Self-hosted e-signature platform for building and signing PDF forms
- 19.7k
pdf-inspector
Rust library that classifies PDFs and extracts their text as Markdown
- Emrik Östling19.2k
ConvertX
Web-based file converter you run on your own server via Docker
25.5kReadest
An ebook reader for EPUB and PDF that syncs your place across devices
- 29.8k
OpenDataLoader PDF
PDF parser that outputs Markdown, JSON and HTML, plus PDF auto-tagging
- 39.3k
PageIndex
Tree-based document index for RAG without vectors or chunking
45.3k
46.9kSiYuan
A local-first note app built from blocks you can link and query
- 46.9k
Paperless-ngx
Self-hosted archive that OCRs, tags, and indexes scanned documents
- 69.2k
Docling
Python library and CLI that converts documents into structured data for AI
Agent frameworks and toolsAI models and runtimesProductivity
- 91.4k
PaddleOCR
OCR toolkit that converts scanned pages and photos to Markdown or JSON
- 95.7k
Puppeteer
Node.js library for scripting headless Chrome and Firefox
- Virgilio Junior35.4k
book-to-skill
Converts technical books and document folders into agent skills
- 19.8k
olmOCR
PDF and image-to-Markdown converter built on a 7B vision-language model
- 191k
MarkItDown
Converts PDFs, Office files, and other documents into Markdown for LLMs