mdflux
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than visi
What is mdflux?
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
Overview of mdflux
What it is
MDFlux is a local-first desktop application that converts documents into clean, structured Markdown. It reads scanned PDFs using built-in OCR, supports batch processing of folders, and runs entirely offline. It is built on Microsoft's MarkItDown and aims to produce fewer tokens than sending document pages as images to vision models.
Key features
- Fewer tokens: Clean Markdown costs about 2 to 6 times fewer tokens than sending pages to a vision model.
- Local and private: Documents never leave the machine. No cloud, no API key, no account.
- Reads scanned PDFs: Built-in OCR recovers text from scans that other tools treat as blank.
- Real structure: Outputs proper Markdown with headings, tables, and lists intact.
- No terminal needed: Portable app. Unzip, run, click through a one-time setup.
- Many formats: Supports PDF, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, TXT, MD, images, and audio.
- Batch a whole folder: Convert everything at once with progress, cancellation, and per-file diagnostics.
- Optional cleanup: Off, rule-based, or an AI pass (local or API). The Changes tab shows what cleanup added or removed.
Use cases
- AI and RAG builders: Feed clean, structured source documents to any model instead of raw text or expensive vision tokens.
- Researchers: Batch-convert papers, reports, and scanned archives into searchable Markdown.
- Developers: Get diff-able, version-controllable text out of binary document formats.
- Writers and analysts: Pull clean copy out of PDFs and Office files without formatting mess.
- Privacy-conscious users: Convert sensitive contracts, records, and decks with nothing ever uploaded.
Getting started
Download the Full or Lite edition from the releases page. Unzip and run the executable. On first launch, a one-time setup installs dependencies (requires internet). After that, conversions run offline.
License and pricing
MDFlux is open source under the MIT license. It is free and requires no account or cloud service.
Based on the project's public README and repository metadata.
