buldezir / lemmary

Lemmary turns scans, PDFs, and office files into an organized library you can search, review, and research in plain language.

Why this job: topics: rag, ocr

1 of 6

What it does

Upload PDF, image, plain text, CSV, Word (.docx), or Excel (.xlsx) documents — one at a time, or a whole folder dropped or picked at once
Full backup and restore. download your whole library — files, OCR text, metadata, thumbnails and taxonomy — as one zip, and restore it into this or another instance
Optional encryption at rest. the volume holds only ciphertext, the instance boots locked until someone signs in, and nobody but your own accounts can unlock it — see docs/encryption.md
Scan straight from a network scanner (Upload → Scan): eSCL/AirScan over the LAN, no driver, found by mDNS or by sweeping the subnet, several pages merged into one document — see docs/scanning.md
Drop files into a watched folder (INGEST_DIR, a bind mount in Docker): scanned on a schedule, subfolders become tags, and the original is kept or deleted as you choose — see docs/setup.md

cp .env.example .env
# Optional: seed OCR/AI keys in .env for first boot (skips those wizard steps)
docker compose up -d

Repos similar to this one
Repo	Stars	Last commit	Licence	Downloads for
Ontos-AI / knowhere	3,953	yesterday	Apache-2.0	No downloads
enoch3712 / ExtractThinker	1,604	55 days ago	Apache-2.0	No downloads
watat83 / document-chat-system	149	28 days ago	MIT	No downloads

More: languages, topics and project record