Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Planned, not doneThe source describes an intention, not a finished result.

Auto-tag receipts and bills in Paperless-ngx with paperless-ai

paperless-ai suggests titles, tags, correspondents and dates for documents in a Paperless-ngx archive, using a local Ollama model or a cloud LLM, with manual review and undo.

Try the promptRead the original (opens in a new tab)

The problem

How it works

paperless-ai is an MIT-licensed add-on that connects to Paperless-ngx with a dedicated user's API token. New or tagged documents go to an AI backend, which proposes a title, tags, correspondent, document type, date and custom fields. It can be limited to your existing tags and correspondents, run on a schedule or from a Paperless webhook, and offers a chat that answers questions about the archive with citations.

Results and limitations

The README lists capabilities and reports no measured accuracy. It offers a manual mode where you approve each suggestion, and a history with undo that restores the original values in Paperless.

Before you try it

Receipts and bills carry personal and financial data: with Ollama the analysis stays on your hardware, while OpenAI, Anthropic and other cloud backends receive the document text. Run version 4.0 or later, because the README says the older setup wizard could be used without logging in and was exploited, and never expose the app to the internet without a VPN or an authenticating proxy. The maintainer calls it a hobby project and says much of v4 was written with AI help. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Paperless-ngx 2.x or 3.x · paperless-ai (Docker) · Ollama or a cloud LLM API
Prerequisites
A running Paperless-ngx instance, Docker, and either a local model through Ollama or an API key for a cloud provider.

Try it yourself: Plan a receipt-tagging rollout

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
I run Paperless-ngx and want paperless-ai with [AI backend] to organise receipts and bills. Propose a small expense tag set (for example [Example tags]), the custom fields to create for amount, currency and vendor, and a trigger tag so only new documents tagged [Trigger tag] are processed. Explain the minimum permissions the dedicated Paperless user needs. Plan a pilot in manual review mode on [Pilot document count] documents, then give me a checklist for comparing suggestions with the originals before any automatic changes are allowed. Do not ask me for API tokens or passwords; tell me where to enter them myself.

Keep manual review on until the pilot shows the suggestions are reliable for your documents.

Related videos

About ollama/ollama

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. clusterzx/paperless-ai README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 11 Nov 2026, 22:04 UTC

    What this source supports
    • Suggests titles, tags, correspondents, document types, dates and custom fields for Paperless-ngx documents
    • Works with OpenAI, Anthropic, Azure OpenAI, Ollama and OpenAI-compatible APIs
    • Manual review mode and a history with undo
    • Needs a Paperless-ngx user with the right permissions and an API token
    • Pre-4.0 setup wizard could be used without login; the README advises updating and not exposing the app publicly
Report a problem

Reported by source

Extract invoice fields locally with a vision model on Ollama

Stephen Sebastian replaced a paid cloud OCR API with Gemma 4 E4B on Ollama to pull date, amount and description from contractor invoice photos on his laptop.

dev.toollama/ollama
Planned, not done

Record and summarise meetings on your own machine with Meetily

Meetily records calls, transcribes them on the device with Whisper or Parakeet, and writes summaries with a local Ollama model or a cloud model you pick.

github.comollama/ollama
Reported by source

Run an open-weight model locally and call it from your code

Install Ollama, pull an open model and call it through the local REST API so prompts stay on your machine.

github.comollama/ollama
Reported by source

Control smart-home devices with a local LLM voice assistant

Connect Home Assistant to a local Ollama model as its conversation agent so you can ask it to control exposed devices privately.

github.comhome-assistant/core, ollama/ollama
Planned, not done

Import recipes and plan the week's meals in self-hosted Mealie with an AI provider

Mealie is a self-hosted recipe manager and meal planner; with an OpenAI-compatible provider it can turn web pages, pasted text or photos into recipes, parse ingredients and suggest tags.

github.comollama/ollama
Planned, not done

Turn public competitor pages into a structured market scan with Crawl4AI

Crawl4AI crawls pages into clean Markdown and extracts fields such as product names and prices with CSS or XPath schemas or an LLM, giving an agent tidy input for a market or competitor comparison.

github.comunclecode/crawl4ai, ollama/ollama