Zettelrobbe

Zettelrobbe is an AI-powered automation tool for Paperless-ngx that automatically tags, sorts, and categorizes your documents using local (Ollama: Mistral,…

  • AI
  • Cloud
  • Media Applications
  • Other
  • Productivity
  • Tools & Utilities
Zettelrobbe is an AI-powered automation tool for Paperless-ngx that automatically tags, sorts, and categorizes your documents using local (Ollama: Mistral, Llama, Phi-3, Gemma) or hosted (OpenAI) models, with an OCR rescue queue for files that fail initial processing.

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.

74/100 Good

Maintained
100last commit 23 days ago
Popular
49267 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
94no serious findings, 1 minor, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 33 days ago

GitHub stars
267
Open issues
18
Last commit
2026-10-29
Latest release
v2026.10.03
License
MIT
Activity
rising

Checked 23 days ago - source: GitHub (admonstrator/zettelrobbe)

Resources & Compatibility

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

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

First-install notes

  • Dependencies Requires a running Paperless-ngx instance and either a local Ollama model (Mistral, Llama, Phi-3, or Gemma) or an OpenAI API key for AI-based document processing. source
  • First run Run the Docker image (admonstrator/zettelrobbe) and point it at your Paperless-ngx instance; it works standalone next to Paperless-ngx and picks up documents it has not seen on a schedule (every 30 minutes by default). source

Fetched 5 days ago - each note links to its source

Alternatives (2)

  • Open Scanner - Open Scanner is a fast and simple-to-use paper-scanning app with AI features to speed up your scanning workflow:
  • Parser - An intelligent data extraction service that automates information processing.

Checked 4 days ago - source: AlternativeTo

Common questions

Can Zettelrobbe merge duplicated correspondents or tags in Paperless-ngx?

Yes. The Duplicates page scans your Paperless-ngx on request, groups similar names, and lets you merge a group into a chosen survivor. Documents move first, leftover objects are deleted only once empty, and each merge is logged locally and can be undone.

What happens to documents with poor OCR quality?

They are sent through a dedicated OCR rescue queue before tagging so they are not lost. You can use Mistral or a local/custom OCR provider for this queue.

How can I restore metadata that Zettelrobbe changed?

Every AI change is recorded in history. You can review what happened, rescan a document on demand, or restore the original metadata with one click.

Where does Zettelrobbe store its configuration and state?

Everything is stored in the ./data volume you mount into the container. This includes data/runtime-overrides.json for your configuration.

Does Zettelrobbe support multi-factor authentication?

Yes, MFA login support is listed as one of its security and reliability features.

How often does Zettelrobbe check Paperless-ngx for new documents?

It checks every few minutes, and the interval is configurable. If a document fails because it is too short or the AI is unavailable, it retries a few times before moving on.

Answers sourced from github.com, zettelrob.be, zettelrob.be

Community

Collected 47 days ago - public community threads