Back to directory

anydoc

A Rust library, with Node.js, Python and WebAssembly bindings, that converts Word, PowerPoint, Excel, RTF, EPUB, CSV and PDF files into clean Markdown for LLMs.

anydoc

anydoc is a Rust library, built by Firecrawl, that converts documents in formats including Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF into clean, GitHub-flavored Markdown, aiming for single-digit-millisecond conversion and one consistent output regardless of the input format. It ships as a CLI, and as bindings for Node.js, Python and the browser through WebAssembly, and a browser demo page runs the WebAssembly build so files are converted locally and never leave the visitor's machine.

The library also ships as an Agent Skill, so agents such as Claude Code, Codex, Cursor and OpenCode can be taught to convert any document they encounter using the anydoc CLI. anydoc reads text-based PDFs locally but does not perform OCR itself; a PDF with scanned or image-only pages can optionally be sent to the hosted Firecrawl Parse API, which OCRs those pages and returns Markdown in the same format, while the Rust crate itself never makes network calls.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.