eikek/docspell

Assist in organizing your piles of documents, resulting from scanners, e-mails and other sources with miminal effort.

What it solves

Docspell is a personal document management system (DMS) designed to help individuals, families, and small businesses organize the "mess" of files generated from scanners, emails, and other sources. It eliminates the tedious manual effort of tagging and categorizing documents by automating metadata extraction.

How it works

The system unifies files from various sources and uses machine learning and Natural Language Processing (NLP) via the Stanford Core NLP library to suggest correspondents, guess tags, and identify dates. It also integrates OCR (Optical Character Recognition) tools like Tesseract and ocrmypdf to make scanned documents searchable through full-text search.

Who it’s for

It is primarily targeted at home users, households, and smaller groups or companies who need a way to digitize and organize their paperwork.

Highlights

  • Automated Metadata: Uses ML and NLP to suggest tags and correspondents based on existing documents.
  • OCR Integration: Performs OCR on documents to enable full-text search.
  • Multi-channel Input: Supports files from scanners, emails, and mobile uploads via an Android app.
  • Flexible Interface: Provides a mobile-friendly SPA web application, a CLI, and a REST/HTTP API.

Related

  • Project
    arc53/DocsGPT

    An open-source platform to create AI agents grounded in your own documents and connected apps, featuring self-hosting and source-cited answers.

  • Project
    clusterzx/paperless-ai

    Paperless‑AI is an open‑source extension for the self‑hosted document manager Paperless‑ngx. It automatically classifies new documents, adds AI‑generated titles/tags, and builds a vector index so you can ask natural‑language questions across your whole archive (RAG chat). It works with any OpenAI‑compatible model—including local Ollama servers—and ships as a Docker image with a simple web UI for configuration and manual processing.

  • Project
    icereed/paperless-gpt

    paperless‑gpt is an open‑source Docker service that plugs into paperless‑ngx, using LLMs (OpenAI, Ollama, etc.) or external OCR APIs to extract text, auto‑generate titles/tags/custom fields, and link related documents via reference numbers, producing searchable PDFs and a simple review UI.

  • Project
    ucbepic/docetl

    DocETL is a declarative and agentic framework for processing large-scale structured and unstructured data using LLMs, automating the optimization of prompts and models for cost and accuracy.

  • Project
    linuxrebel/DocuBrowser

    DocuBrowse is a cross‑platform desktop/web app that indexes a wide range of document types and lets you search them by keywords and by AI‑generated semantic similarity, all using locally‑run Ollama models. It offers deep‑link passage navigation, on‑demand AI summaries, PII filtering, and runs entirely offline.