I built Kintara because apparently having too many hobbies eventually leads to building your own document management system

Description and use

Kintara is a self‑hosted document library that runs in Docker, automatically indexes PDFs, Markdown, and text files, generates thumbnails and metadata, and offers optional AI features for summarization, cover image generation, and verified document search.

Problem

Users need a simple, self‑hosted document library that automatically indexes PDFs, Markdown, and text files, provides full‑text search, metadata management, and optional AI enhancements without forcing AI usage.

Outcome

Kintara transforms a chaotic document collection into an organized, searchable library with optional AI enhancements, all running in Docker and accessible from any device.

Workflow

• 1. Deploy Kintara via Docker on a NAS or local machine.
• 2. Point Kintara to the folder containing PDFs, Markdown, or text files.
• 3. Kintara watches the folder, indexes new files, extracts text and metadata, and generates thumbnails and cover images.
• 4. Access the library through a browser or PWA from any device.
• 5. Use optional AI features: enable OpenAI or Gemini to summarize documents, suggest metadata, generate cover images, or search for passages with verification.
• 6. Manage collections, tags, and sharing permissions via the web interface.

Evidence

Drop PDFs, Markdown, or text files into the directory and it indexes them automatically, extracts searchable text and metadata, generates thumbnails, and makes the whole library available through a browser or installable PWA.

Source

I added an option to use OpenAI or Gemini, and with so few tokens being spent, it's a fraction of a cent to use most of them, aside from the cover image generation, which is bit more, but makes the library look so much prettier!

Source

Kintara asks for actual passages with page numbers, verifies the quote against extracted page text on the server, then verifies it again against the rendered PDF.

Source