# clusterzx/paperless-ai

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

Repository: https://github.com/clusterzx/paperless-ai
Canonical: https://ross.abutalabs.com/products/paperless-ai
Homepage: https://clusterzx.github.io/paperless-ai/
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai, automation, paperless, paperless-ngx, gemma, llama, mistral, ollama, phi
Last push: 2026-08-22T07:41:22+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 55, longevity 45
- inputs: {"age_days": 640, "days_push": 11, "days_rel": 302, "gap_med": 0, "n_releases_24m": 58}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5910, forks 327 (observed 2026-08-28T04:09:32.183712+00:00)

## What it is
A self-hosted web application that automatically analyzes, tags, and classifies documents in Paperless-ngx using LLMs via OpenAI-compatible APIs, Ollama, and similar backends. It also provides RAG-based semantic search and natural language chat over the document archive through a web interface.

## Use cases
- automatically tag and classify documents in paperless-ngx
- assign titles, correspondents, and document types with AI
- chat with my document archive in natural language
- search scanned documents semantically instead of by keywords
- run local LLM document analysis with Ollama for privacy
- process new paperless-ngx documents automatically
- manually review AI tagging for sensitive documents

## When to choose
- you use Paperless-ngx and want automated AI tagging and metadata assignment
- you want RAG-based Q&A over your personal document archive
- you prefer local models via Ollama for privacy-sensitive documents

## When to avoid
- you don't use Paperless-ngx as your document management system
- you need actively maintained software - the repo is currently unmaintained pending a rewrite
- you want built-in OCR or PDF conversion - documents must already be ingested by Paperless-ngx

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, llm-inference, rag, nlp, ocr, workflow-automation, chat-interface
- domain: artificial-intelligence, large-language-models, pdf, self-hosted, developer-tools
- platform: self-hosted
- tags: paperless-ngx, document-management, auto-tagging, ollama, openai-api, document-chat, semantic-search, retrieval-augmented-generation, automation, docker, web-server, nodejs

## Member repositories
- clusterzx/paperless-ai (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:32.183712+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:51:16.677519+00:00, confidence not recorded.
  - readme: https://github.com/clusterzx/paperless-ai (fetched 2026-08-28T04:09:32.183712+00:00, sha 305cec8a0a85)
  - homepage: https://clusterzx.github.io/paperless-ai/ (fetched 2026-08-29T08:46:54.476459+00:00, sha 0c855aa64614)
- Data as of 2026-08-30T08:39:29.467469+00:00.