Point it at a folder of scanned PDFs, Office files, emails or photos of documents. It runs OCR only on the pages that need it, reads every page, and writes back four files: an index, a chronological timeline, a review report, and instructions ready to paste into an AI project. Classification runs a small open model on your own machine through Ollama. No account, no API key, no upload. Free and open source under GPL-3. Windows 10 and 11.