Anydoc

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.

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.

• 01Consistent Markdown output across 14+ document formats
• 02High-performance Rust core with sub-5ms median conversion time
• 03Native bindings for Node.js and Python
• 04Content-based format detection independent of file extensions
• 05Full document structure support including tables, footnotes, and embedded assets
• 06Local PDF parsing via pdf-inspector with no OCR required for text-based files