Open Source · Self-Hosted

Paperless-AIssist

AI-powered document processing for Paperless-ngx. Drop a tag on a document — the LLM handles the rest.

Sponsor on GitHub View on GitHub

Smart Classification

Automatically assigns correspondents, document types, and tags using your LLM — no manual sorting.

Vision OCR

Send document pages to a vision model for high-quality OCR on scanned PDFs, with optional text correction.

Custom Field Extraction

Define extraction prompts to pull structured data — invoice totals, dates, reference numbers — straight into Paperless custom fields.

Multi-Provider LLM

Supports Ollama (local), OpenAI, and Grok. Mix providers — use a local model for classification and a vision model for OCR.

Multilingual UI

The web interface ships with English and German translations. More languages can be added by editing a single JSON file.

Get Started in Seconds

docker run -d \
  -p 8000:80 \
  -v paperless-aissist-data:/app/data \
  nyxtronlab/paperless-aissist

Then open http://localhost:8000 and connect your Paperless-ngx instance.