Paperless-AIssist

AI-powered middleware that connects Paperless-ngx to LLM providers (Ollama, OpenAI, Grok, OpenRouter) for automated document classification, OCR…

  • AI
  • Productivity
AI-powered middleware that connects Paperless-ngx to LLM providers (Ollama, OpenAI, Grok, OpenRouter) for automated document classification, OCR post-processing, and structured data extraction via configurable tag-based workflows.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

67/100 Good

Maintained
100last commit 13 days ago
Popular
3882 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
70no serious findings, 14 minor, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 36 days ago

GitHub stars
82
Open issues
1
Last commit
2026-11-08
Latest release
v0.14.0
License
MIT
Activity
declining

Checked 10 days ago - source: GitHub (nyxtron/paperless-aissist)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Start the app with Docker Compose Docker Compose (a one-file way to start the app's containers) should be run with docker compose up -d in the folder containing your compose file. If you don't start it this way, the web UI and document processing won't be running. source
  • Make sure document folders exist Create or point your setup at the consume and media folders before first use. consume is where new documents are dropped, and media stores processed files; if they're missing or not backed up, documents can fail to process or be lost. source
  • Keep Redis local if you use it Redis (a small in-memory data store Paperless uses for background jobs) may need to run as a separate container. If so, start it with the provided Docker command and leave port 6379 for local use only, because blocking it can leave document tasks stuck. source
  • LLM Provider Setup Configure at least one LLM provider (Ollama, OpenAI, Grok, or OpenRouter); text and vision models are set up separately per workflow step. source

Fetched 38 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Can I require sign-in to the Paperless-AIssist web UI?

Yes, optional authentication can protect the web UI with your Paperless-ngx credentials. It is disabled by default.

Which host port does the Docker example expose?

The quick-start Docker command maps host port 8000 to container port 8080.

Which data directory should I persist for Paperless-AIssist?

The quick-start Docker command mounts persistent data at /app/data.

Can I keep metadata generation local and use a paid vision model only for OCR?

Yes, text and vision models are configured separately. You can run metadata generation on a local Ollama model and reserve a paid vision model for documents tagged for OCR.

What happens if the AI is unsure about metadata classification?

In decision mode, an unsure pick leaves the field unchanged and tags the document for review.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads