ibrahimqureshae/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.

What it solves

MDFlux converts various document formats into clean, structured Markdown. This solves the problem of losing structure (headings, tables, lists) when extracting raw text or spending excessive tokens and compromising privacy by sending document images to cloud-based vision models. It specifically addresses the issue of scanned PDFs, which often appear blank to standard text extractors.

How it works

MDFlux is a desktop application built on Microsoft's MarkItDown library. It uses a local Python environment to process files—including PDFs, Office documents, EPUBs, and audio—and converts them to Markdown. It includes built-in OCR for scanned pages and images. Users can choose between three cleanup modes: none, rule-based, or an AI-powered pass (using either local or API-based models) to tidy up the extraction.

Who it’s for

  • AI and RAG builders: Those needing clean, structured source documents for LLMs to reduce token costs.
  • Researchers: People batch-converting papers and scanned archives into searchable text.
  • Developers: Users wanting version-controllable text from binary formats.
  • Writers and analysts: Those extracting clean copy from PDFs and Office files.
  • Privacy-conscious users: Users who need to process sensitive documents entirely locally.

Highlights

  • Token Efficiency: Reduces token usage by 2 to 6 times compared to vision models.
  • Local-first: Documents are processed on-device, ensuring privacy and offline capability.
  • Broad Format Support: Handles PDF, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, TXT, images, and audio.
  • Batch Processing: Ability to convert entire folders of mixed files concurrently with progress tracking.
  • Built-in OCR: Recovers text from scanned, image-only PDFs.
  • User-Friendly: Portable app with no terminal required for standard users.

Related

  • Project
    microsoft/markitdown

    MarkItDown is a Python library/CLI that converts many document types (PDF, Office files, images, audio, video, web content, archives, etc.) into Markdown, targeting large‑language‑model pipelines. It works offline for common formats and can optionally call Azure Document Intelligence or Azure Content Understanding for higher‑quality, multimodal extraction. Plugins (e.g., OCR via LLM vision) extend its capabilities, and a simple API lets developers integrate conversion into their own code.

  • Project
    magicrew/doc7

    A document conversion tool that turns PDFs, Office files, and images into AI-ready Markdown using multimodal vision models, supporting local inference for privacy and cost-efficiency.

  • Project
    firecrawl/anydoc

    anydoc is a pure‑Rust library (with Node, Python, and WebAssembly bindings) that converts 14 office‑document formats into consistent GitHub‑Flavored Markdown in a few milliseconds. It preserves document structure, supports optional hosted OCR for scanned PDFs, and is packaged as a CLI, an Agent Skill, and language‑specific SDKs, making it ideal for LLM‑oriented pipelines that need fast, uniform text extraction.

  • Project
    oomol-lab/pdf-craft

    PDF Craft is a Python library that OCR‑extracts scanned PDFs, preserving structure (chapters, tables, footnotes, images) and exports the result as editable Markdown or EPUB. It supports remote or local DeepSeek‑based OCR, optional translation via a text LLM, and can write translated text back into a new PDF. The package offers synchronous and async APIs, reusable extraction files (.pcex), and an online demo for quick testing.

  • Project
    pymupdf/PyMuPDF

    A high-performance Python library for extracting, analyzing, and converting PDF and Office documents, featuring LLM-ready Markdown and JSON output for AI pipelines.