anymd

Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts

What is anymd?

Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.

Overview of anymd

What it is

an anymd is a tool that converts any file into clean Markdown for AI agents. It supports PDF, Word, PowerPoint, Excel, EPUB, HTML, web pages, images (OCR), audio and video (metadata, subtitles, transcripts). It is a fast Rust MCP server and CLI that runs on your machine with no API key required. The project is licensed under MIT and is open source.

Key features

  • Fast: Native Rust converts in parallel, page by page. On 38 benchmark documents, anymd takes 11.5 s total; docling 2,432.4 s (212×), markitdown 75.6 s (7×), marker 7,104.5 s (1,532×).
  • Accurate: A layout engine rebuilds words from glyph gaps, puts two-column papers in reading order, and recovers tables, including borderless ones.
  • Lean on tokens: Pages come back as Markdown with citation anchors, a small front-matter header, and compact tables. A token budget and a cursor keep large documents within your agent's context.
  • Every format, one call: One tool reads every format listed. It also accepts web URLs and whole directories, and search looks across all of them.
  • Local and private: Nothing is uploaded. OCR uses installed local doc-VLM models or tesseract; transcripts use ffmpeg and bundled Qwen3-ASR. OCR setup and ASR model downloads require explicit opt-in.
  • MCP tools: Exposes four tools: outline, read, search, and inspect.

Use cases

  • Converting PDF, Word, PowerPoint, Excel, EPUB, HTML, images, audio, and video files into clean Markdown for use by AI agents such as Claude Code, Codex, Cursor, VS Code, Claude Desktop, Windsurf, and Gemini CLI.
  • Searching across multiple files and folders for specific text using the search tool.
  • Extracting tables, reading order, and structured content from complex documents (e.g., two-column papers, financial tables, forms).
  • Processing sensitive documents locally without uploading to any external service.

Getting started

bash npx -y @sylphx/anymd setup npx -y @sylphx/anymd report.pdf > report.md

License and pricing

MIT license, open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/sylphxaianymd.svg)](https://yunodb.com/tools/sylphxaianymd?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/sylphxaianymd?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/sylphxaianymd.svg" alt="Featured on YunoDB" height="20"></a>