Paperless-AI
AI auto-tagging and document chat for Paperless-ngx (currently unmaintained).
Quick answer
Paperless-AI is an AI auto-tagging and document chat for Paperless-ngx (currently unmaintained), listed under Document processing. A typical small-business use: auto-file scanned invoices and letters in Paperless-ngx. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: MIT, which allows internal business use. Activity is low: the last commit was on Mar 31, 2026.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is Paperless-AI?
Paperless-AI is an extension for the Paperless-ngx document archive. It detects new documents, uses an OpenAI-compatible model or Ollama to set the title, tags, document type and correspondent, and adds RAG chat across the archive. The README says the repository is currently not maintained.
Where it fits in a 10–200 person business
- Auto-file scanned invoices and letters in Paperless-ngx
- Ask questions such as "when did we sign the office lease?"
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Paperless-AI? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep the copyright notice. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does Paperless-AI need?
The project does not publish a minimum CPU/RAM figure, so we leave it blank rather than guess.
No official hardware requirements published. Requires an existing Paperless-ngx instance.
How much does it cost to host Paperless-AI per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy Paperless-AI
Method: Docker
# See the installation wiki for the docker-compose file:
# https://github.com/clusterzx/paperless-ai/wiki/2.-InstallationFrom the official instructions: github.com/clusterzx/paperless-ai#readme. Always check the source for the current version before you run it.
Known gotchas when self-hosting Paperless-AI
Paperless-AI FAQ
How much RAM does Paperless-AI need?
Paperless-AI does not publish an official RAM figure, so we do not state one. Requires an existing Paperless-ngx instance.
How much does it cost to self-host Paperless-AI?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is Paperless-AI free for commercial use?
Paperless-AI is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep the copyright notice. This is a summary, not legal advice.
What are common problems when self-hosting Paperless-AI?
The maintainer states the repo is currently not maintained and may not be continued, partly because Paperless-ngx is adding official AI integration. On first install, restart the container after finishing setup (API keys, preferences) so the RAG index is built.
Is Paperless-AI still maintained?
Activity is low (no commit in 180+ days). Last commit: Mar 31, 2026. Latest release: v3.0.9 (Nov 4, 2025). Checked Oct 22, 2026.
How do I install Paperless-AI?
The official method is Docker. The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/clusterzx/paperless-ai#readme
Sources
- GitHub repository: github.com/clusterzx/paperless-ai
- Official documentation: github.com/clusterzx/paperless-ai/wiki/2.-Installation
- License text: github.com/clusterzx/paperless-ai/blob/main/LICENSE
- Hardware requirements, Deploy instructions, Gotcha 1, Gotcha 2: github.com/clusterzx/paperless-ai#readme
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.