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 automatically indexes files, extracts metadata, and offers optional AI features like summarization and cover image generation, simplifying the organization of large PDF and Markdown collections.

Problem

Managing a growing collection of PDFs, Markdown, and text files with inconsistent metadata and limited searchability.

Outcome

Kintara transforms a chaotic document collection into an organized, searchable library with optional AI enhancements, reducing manual metadata cleanup and improving accessibility across devices.

Workflow

• 1. Deploy Kintara via Docker and point it at a shared folder (e.g., NAS).
• 2. Drop PDFs, Markdown, or text files into the folder.
• 3. Kintara watches the folder, indexes new files, extracts text and metadata, and generates thumbnails.
• 4. Access the library through a browser or PWA from any device.
• 5. (Optional) Enable AI features: OpenAI or Gemini for summarization, metadata suggestions, cover image generation, or chat search.
• 6. Use the UI to tag, favorite, or share documents with other users via OAuth.
• 7. Verify AI‑generated passages by comparing extracted text and rendered PDF to ensure accuracy.

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.

Source

Kintara can read the document and suggest a title, author, summary, keywords, DOI, ISBN, and publication year.

Source