paperless-ngx

Paperless-ngx is a document management system for digitizing and managing paper documents. It OCR-scans documents for text recognition, automatically classifies and tags them, and builds a full-text searchable archive.

• OCR processing via Tesseract-based text recognition for searchable PDF generation
• Auto-classification using machine learning for document categorization and tagging
• Full-text search across all OCR-processed documents
• Email ingestion for automatic import of PDF attachments from email
• Barcode splitting for automatic multi-document separation using barcode separator sheets
• Workflows for document assignment, approval, and consumption management

Built with Python on Django, Paperless-ngx is Docker self-hosted. It is the definitive tool for going paperless by converting paper documents into searchable digital archives.