firecrawl/anydoc

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

What it solves

anydoc is a high-performance library designed to convert a wide variety of office documents into clean, GitHub-Flavored Markdown. It solves the problem of inconsistent and slow document parsing across different file formats, providing a single, consistent output format that is ideal for LLM-ready data preparation.

How it works

The library is written in pure Rust for speed and does not rely on ML models or external services. It uses a multi-step process:

  1. Format Detection: It identifies the file type based on content markers (bytes) rather than relying on file extensions.
  2. Format Parser: Each supported format has its own parser that converts the document into a shared internal document model (containing blocks, inlines, tables, and assets).
  3. GFM Serializer: This shared model is then rendered into Markdown via a single serializer, ensuring identical behavior for elements like tables and footnotes across all input formats.
  4. PDF Handling: Text-based PDFs are converted directly to Markdown using pdf-inspector.

Who it’s for

  • AI Developers: Those building RAG pipelines or LLM applications that need to ingest a mixed bag of office documents.
  • Agentic Workflows: Developers creating AI agents that can read and process local files via the provided "Agent Skill" integration.
  • Software Engineers: Anyone needing a fast, local, and consistent document-to-markdown converter with bindings for Node.js, Python, and Rust, or the ability to run it in the browser via WebAssembly.

Highlights

  • Broad Format Support: Supports 14 formats including Word, PowerPoint, Excel, OpenDocument, and PDF.
  • Extreme Speed: Median conversion time is under 5ms per document.
  • Consistent Output: A shared document model ensures that formatting (like LaTeX equations for math) is uniform across all formats.
  • Local Processing: No external API calls or ML models required for core conversion, with a WebAssembly version for local browser-based conversion.
  • Agent Ready: Integration as an Agent Skill allows AI agents to easily adopt the document reading capability.

Related

  • Project
    microsoft/markitdown

    A Python utility that converts various file formats (PDF, Office, audio, video, etc.) into Markdown to optimize them for LLM consumption and text analysis pipelines.

  • Project
    pymupdf/PyMuPDF

    A high-performance Python library for extracting and manipulating PDF and Office documents, featuring specialized tools for converting documents into LLM-ready Markdown for RAG pipelines.

  • 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
    ibrahimqureshae/mdflux

    MDFlux is a Windows‑only, portable desktop app that converts PDFs, Office files, HTML, CSV, images, audio, and many other formats into clean, structured Markdown. It runs locally, includes OCR for scanned PDFs, offers batch processing, and optional LLM‑based cleanup. By producing plain Markdown instead of image pages, it reduces token usage 2‑6×, lowering inference cost for RAG pipelines while keeping data private.

  • Project
    docling-project/docling

    A document parsing tool that converts complex PDFs, Office files, and multimodal content into structured Markdown or JSON for use in generative AI and RAG pipelines.