anydoc
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
anydoc turns Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF files into clean Markdown, the format LLMs read best. Every format lands in one shared document model and one Markdown writer, so a spreadsheet table and a Word table come out the same shape. Firecrawl built it, and it's MIT licensed and free.
It's a library, not a server. The core is Rust, with packages for Node, Python and the browser through WebAssembly, plus a CLI: npx @firecrawl/anydoc report.docx. No API key, nothing to host, and a reported median under 5 ms per document.
The paywall is OCR. anydoc does none, so a scanned PDF fails with NeedsOcr. Opt in with --ocr hosted and that file goes to Firecrawl Parse at 1 credit per page: 1,000 free credits a month, then Hobby at $19/month. Solo and small teams: free. Teams buried in scans: budget for Parse or bring your own OCR.
The catch: the benchmark that makes it look great is Firecrawl's own, judged by an LLM on a private corpus, with no PDF row in the per-format results. Hosted OCR also ships the whole document to Firecrawl, not just the scanned pages. Test your ugliest real files first.
Free vs Self-Hosted vs Paid
free self hosted paid cloudFree: The whole library under MIT: Word (.doc/.docx/.docm), PowerPoint, Excel (including xlsb), OpenDocument, RTF, EPUB, CSV and text-based PDF to GitHub-Flavored Markdown, with equations as LaTeX, footnotes, speaker notes and embedded assets on the document model. CLI, Node, Python, Rust and WebAssembly packages plus an agent skill (npx skills add firecrawl/anydoc). Runs fully local; the Rust crate never makes network calls.
Self-hosted: Nothing to deploy. npm install @firecrawl/anydoc, pip install firecrawl-anydoc, cargo add anydoc, or npm install @firecrawl/anydoc-wasm for the browser. No account, no key, no infrastructure. The browser demo converts files locally.
Paid: Only scanned or image-only PDFs. Opting in with ocr: 'hosted' / --ocr hosted sends the whole document to Firecrawl Parse: no signup at low limits, or set FIRECRAWL_API_KEY for your plan's limits. Parse bills 1 credit per page, and re-uploads are billed again. Firecrawl plans share one credit balance across scraping, search and parsing: Free 1,000 credits/month with no card; Hobby $19/month billed monthly or $16/month billed annually for 5,000; Standard $83/month billed annually for 100,000; Growth $333/month billed annually for 500,000; Scale $599/month billed annually for 1,000,000. Parse itself accepts nine extensions (.pdf, .docx, .doc, .odt, .rtf, .xlsx, .xls, .html, .htm), so PowerPoint, EPUB and CSV conversion stays local-only.
Free and MIT for every digital document, with no key and no server. Scanned PDFs need Firecrawl Parse at 1 credit per page: 1,000 free pages a month, then Hobby at $19/month ($16/month billed annually) for 5,000.
What to do by team size
- Solo
- free; local library, no key, no server
- Small team
- free; Firecrawl's 1,000 free credits a month cover occasional scanned PDFs
- Medium team
- free for digital documents; Hobby or Standard Firecrawl plan only if scanned PDFs are routine
- Large team
- free library; Standard ($83/month billed annually for 100,000 pages) or your own OCR stack for scanned volume
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
Similar Tools
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
Tesseract Open Source OCR Engine (main repository)
Get your documents ready for gen AI
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 91+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Open-source, self-hosted file-processing tool. Convert, compress, OCR, transcribe & run local AI across image, video, audio, PDF & documents, via UI, REST API & pipelines. Your files never leave your network.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: MIT License
Use freely, including commercial. Just keep the license.
Commercial use: ✓ Yes
About
- Owner
- Firecrawl (Organization)
- Stars
- 23,423
- Forks
- 1,521
Explore Further
More tools in the directory
rea
Reverse engineer anything with agents, from app behavior down to native binaries.
441.9k ★openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
394.2k ★everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
299.3k ★Featured in The Open Source Drop #21