paperless-gpt

What is paperless-gpt?

paperless-gpt runs next to an existing paperless-ngx archive. It uses an LLM (OpenAI, Mistral, Azure OpenAI, Anthropic or local Ollama) or an OCR service (Azure Document Intelligence, Google Document AI, Docling) to re-read messy scans, then suggests titles, tags, correspondents, created dates and custom fields that you can review. It can also link related documents, such as a reminder to the invoice it cites, and produce searchable PDFs.

Where it fits in a 10–200 person business

• Clean up OCR and naming for a scanned invoice and contract archive already in paperless-ngx
• Auto-tag incoming mail scans with a local Ollama model so documents stay on your own hardware
• Link reminders, credit notes and delivery notes to the invoice or contract they reference

These use cases are our editorial suggestions, not claims made by the project.

Can a business use paperless-gpt? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does paperless-gpt phone home?

Checked against the project's own docs and repository on Oct 27, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does paperless-gpt need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: Not needed for the app itself. A GPU only matters if you run the LLM locally (for example with Ollama).

No official RAM or disk figures. Requires a running paperless-ngx (tested with 2.20.x and the 3.0.0 beta) and access to an LLM provider.

Source: github.com/icereed/paperless-gpt#prerequisites

How much does it cost to host paperless-gpt per month?

How to deploy paperless-gpt

Method: Docker Compose

# add to the docker-compose.yml that runs paperless-ngx
services:
  paperless-gpt:
    image: icereed/paperless-gpt:latest
    environment:
      PAPERLESS_BASE_URL: "http://paperless-ngx:8000"
      PAPERLESS_API_TOKEN: "your_paperless_api_token"
      LLM_PROVIDER: "openai"
      LLM_MODEL: "gpt-4o"
      OPENAI_API_KEY: "your_openai_api_key"
    volumes:
      - ./prompts:/app/prompts
      - ./config:/app/config
      - ./db:/app/db
    ports:
      - "8080:8080"
    depends_on:
      - paperless-ngx

From the official instructions: github.com/icereed/paperless-gpt#docker-compose. Always check the source for the current version before you run it.

Known gotchas when self-hosting paperless-gpt

• paperless-gpt has no built-in authentication and listens on all interfaces by default. Anyone who can reach the port can rewrite documents and spend your API keys, so put it behind an authenticating reverse proxy or a VPN. source
• PDF_REPLACE=true deletes the original document after upload and cannot be undone. On paperless-ngx 3.0+ use PDF_UPLOAD_MODE=version instead, which keeps the original as the previous version. source
• In the default "new" upload mode some metadata is not copied to the new document, including notes and fields added by other plugins. source

Alternatives in Document processing

• PaddleOCR OCR toolkit and document AI engine that turns scans, images and PDFs into LLM-ready text, Markdown or JSON. Compare PaddleOCR vs paperless-gpt
• MinerU Document parser that converts PDFs, scans and Office files into clean Markdown or JSON for LLMs and RAG. Compare MinerU vs paperless-gpt
• Unstract No-code LLM platform that turns invoices, forms and other documents into structured JSON. Compare paperless-gpt vs Unstract
• Paperless-AI AI auto-tagging and document chat for Paperless-ngx (currently unmaintained). Compare Paperless-AI vs paperless-gpt

Sources

• GitHub repository: github.com/icereed/paperless-gpt
• Official documentation: github.com/icereed/paperless-gpt#getting-started
• License text: github.com/icereed/paperless-gpt/blob/main/LICENSE
• Hardware requirements: github.com/icereed/paperless-gpt#prerequisites
• Deploy instructions: github.com/icereed/paperless-gpt#docker-compose
• Gotcha 1: github.com/icereed/paperless-gpt#security
• Gotcha 2, Gotcha 3: github.com/icereed/paperless-gpt#pdf-upload-to-paperless-ngx
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 27, 2026