Firecrawl's anydoc converts 14 document formats to Markdown in one Rust library

Firecrawl released anydoc, an open source Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF files into GitHub-flavored Markdown, according to the project's repository.

The library detects format by content rather than file extension, routes documents through format-specific parsers into a shared document model, then renders to Markdown. It ships with bindings for Node.js (with TypeScript types), Python and browsers via WebAssembly.

In the project's benchmarks against six competitors, anydoc reported a median conversion time of 4.4 milliseconds and was the only tool to handle all 14 tested formats. It scored 81 out of 100 on quality metrics.

The repository has passed 12,400 stars under an MIT license. For teams feeding documents into LLM pipelines, a fast local converter removes a common bottleneck and a dependency on hosted parsing APIs.