Back to News
Firecrawl•August 4, 2026
Anydoc
Open Source
document-conversion
markdown
rust
llm-data-prep
### TL;DR
Anydoc is a high-performance Rust library designed to convert various office document formats, including Word, PowerPoint, Excel, and PDF, into clean, LLM-ready GitHub-Flavored Markdown. It provides consistent output across different file types and includes language bindings for Node.js and Python.
Key Insights & Metrics
Pricing
Open source (MIT License)
Cost structure
Version
0.1.2
Current release version
Hardware
Standard development environment; Rust toolchain for building from source
Compute requirements
Category
Open Source
Licensing model
Region
United States
Primary region
Key Features
- Consistent Markdown output across 14+ document formats
- High-performance Rust core with sub-5ms median conversion time
- Native bindings for Node.js and Python
- Content-based format detection independent of file extensions
- Full document structure support including tables, footnotes, and embedded assets
- Local PDF parsing via pdf-inspector with no OCR required for text-based files
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!