firecrawl/anydoc

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF files into GitHub-Flavored Markdown, with Node.js, Python and WebAssembly bindings. It also ships as an agent skill but cannot read scanned pages on its own.

How it helps ATF

Could be a reference for turning office files into Markdown before Company Brain connects them with work, and for giving agents in Harness a document-reading skill.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• hugohe3/ppt-master
  Turns documents or topics into editable, native PowerPoint decks with native shapes, transitions, animations, charts and tables. It can also add audio narration from speaker notes and follow existing .pptx templates.
• firecrawl/pdf-inspector
  A Rust library that detects whether a PDF is text-based, scanned, image-based or mixed, and shows which pages need OCR. It extracts position-aware text and converts text PDFs to Markdown, including tables and multi-column layouts.
• LaoFeng-mouse/flyingmouse-format
  FlyingMouse Format is an offline Windows desktop app that converts images, documents, spreadsheets, slides, PDF, audio and video between formats, with OCR and batch conversion. It bundles FFmpeg, LibreOffice, Poppler and Tesseract.
• chuspeeism/dashi-ppt-skill
  An agent skill that turns documents into web presentations in 12 visual themes. Each page has in-browser controls for editing text, layout and media, and the result can be exported to HTML, PDF or editable PPTX.
• lynote-ai/humanize-text
  An open-source pipeline that rewrites AI-generated text into more natural prose. It runs two LLM rewrites at temperature 1.3, then two translation hops through different machine translation engines, and publishes every intermediate step.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.