#1919th of 50 in Data and scraping for AIFor data and documents, documents and ocr
anydoc
Rust library converting Office, EPUB, CSV and PDF files to Markdown
- Stars
- 23.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- Rust
2,294 on 4 Aug 202623,490 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Firecrawl is hiring: 24 open roles
Overview
anydoc parses Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and text-based PDF files into a shared document model and renders GitHub-Flavored Markdown. It ships as a Rust crate with Node.js, Python and WebAssembly bindings, a CLI, and an Agent Skill. Scanned PDFs need an opt-in call to the hosted Firecrawl Parse API.
Who it is for: Developers feeding mixed office documents into LLM or RAG pipelines
Strengths
- Covers 14 formats through one Markdown serializer, so tables and footnotes render consistently
- Pure Rust with no ML models; README reports 4.4 ms median conversion per document
- Detects format from file content, so mislabeled extensions still convert
- Bindings for Node, Python and browser WASM; the demo page converts files locally
Weaknesses
- No local OCR; scanned PDFs fail with NeedsOcr unless sent to hosted Firecrawl Parse
- Hosted OCR uploads the whole document, since Parse has no page selection
- Benchmark corpus is not redistributable, so published scores cannot be reproduced
- CSV needs an explicit format or extension because it has no content signature
What it needs
- no GPU
- Needs Firecrawl Parse API (optional, for OCR)
Quick answers
Is anydoc open source?
Yes. Its code is on GitHub under the MIT license.
Does anydoc need a GPU?
No, it runs without one.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |