Kreuzakt is a project that takes the best parts of Paperless, drastically improves the OCR using VLLMs, and throws out 99% of the complexity. Take every boring document in your life and make them all instantly easy to find, and (optionally) let AIs search them to answer questions for you.

• Kreuzakt uses a single Docker container with an SQLite database, there aren't a ton of moving parts
• Rather than use Tesseract, Kreuzakt uses LLMs to do OCR (by default via OpenRouter but Ollama/Local LLMs work as well) via Kreuzberg. This drastically improves OCR accuracy, and by extension, search accuracy.
• Kreuzakt provides a remote MCP server - connect Claude Desktop, Cursor, or any other MCP client to Kreuzakt and ask questions about your documents
• Kreuzakt uses an LLM to also derive a title / description / original date for every document, out of the box. Zero manual curation / toil work.
• Metadata can always be regenerated from the source documents, the only thing you need to migrate is the originals

• Kreuzakt always preserves your original documents, it never edits them directly
• Ingestion based on file watches works the same, drop documents into the 'ingest' folder and it will automatically be processed

services:
  kreuzakt:
    image: ghcr.io/anaisbetts/kreuzakt:latest
    ports:
      - "3000:3000"
    environment:
      OPENROUTER_KEY: ${OPENROUTER_KEY}
      TZ: Europe/Berlin  # Set your local timezone
    volumes:
      - ./docs:data
    restart: unless-stopped

Drop this in a docker-compose.yml, set OPENROUTER_KEY in your environment or a .env file, and run docker compose up -d. The web UI is at http://localhost:3000.

The ./docs folder will be initialized with directories including ./data/ingest, ./data/originals, and ./data/thumbnails.

1. docker-compose up -d
2. Drop all of your documents into the ingest folder - they will eventually all move to the originals folder. You can see the progress at /settings - if you have a lot of documents it might take a bit.
3. If you've got an existing Paperless install, you can run the import
4. You can also simply drag-drop a bunch of files onto the main page

I'm too lazy to do the math on exactly how much per-page it costs, but for perspective, importing 440 documents from Paperless (a few of which were up to 80pgs long), cost me ~$5.

Everything lives under /data by default — the SQLite database, originals, thumbnails, and the ingest folder. If you want to split things up, override with individual env vars and mount each path separately:

Kreuzakt exposes a remote MCP endpoint at /mcp (Streamable HTTP). Replace the hostname in the snippets below with wherever you serve the app — for example https://docs.your-tailnet.ts.net/mcp when using Tailscale Serve. Most clients will not talk to plain http, so terminating TLS (Serve, a reverse proxy, etc.) is the usual approach.

{
  "mcpServers": {
    "docs": {
      "command": "npx",
      "args": ["mcp-remote@latest", "https://docs.your-tailnet.ts.net/mcp"]
    }
  }
}

{
  "mcpServers": {
    "docs": {
      "type": "http",
      "url": "https://docs.your-tailnet.ts.net/mcp"
    }
  }
}

• "Find invoices from Deutsche Telekom."
• "What was my health insurance number again?"
• "How much did I pay in taxes last year"

Prerequisites: Bun (the project runs Next.js and scripts through Bun; see package.json) and a Rust toolchain for the Kreuzberg extraction CLI.

1. Install dependencies: bun install
2. Build the local extraction CLI: cargo build -p kreuzakt-kreuzberg
3. Copy .env.local.example to .env.local and set at least one way to reach an OpenAI-compatible API. The usual choice is OPENROUTER_KEY. For a local LLM, set OPENAI_DEV_URL, OPENAI_DEV_KEY, and optionally OCR_VLM_DEV_MODEL / METADATA_LLM_DEV_MODEL. See .env.local.example for all variables the app and tooling recognize.
4. Start the dev server: bun dev. The app listens on port 3000 by default (PORT). Runtime data defaults to ./data (SQLite, ingest, originals, thumbnails) unless you override DATA_DIR or individual path variables.

Other useful commands:

• bun test — unit tests
• cargo test — Rust extraction CLI tests
• bun run test:integration — integration tests (loads .env.local via --env-file; requires Paperless-related vars when those tests run)
• bun storybook — UI development on port 6006

POST /api/documents/export-text exports every document whose SQLite content column is non-empty as a ZIP of .txt files. Each file is named {id}-{sanitized-title}.txt and begins with YAML frontmatter (original_filename, document_url, original_url) followed by the extracted document body. The response is an application/zip download named kreuzakt-text-export-YYYYMMDD-HHmmss.zip. Returns 400 if there is no exportable content.

curl -X POST http://localhost:3000/api/documents/export-text -o export.zip

It uses the library Kreuzberg, and it is a tool to help you with your "Akte" (files/documents). Just like "Berghain" is a portmanteau of "Kreuzberg" and "Friedrichshain", the two districts in Berlin that it sits between. (today you learn!)