# firecrawl/anydoc

> Rust library that converts office documents (Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, PDF) into clean Markdown, with Node.js, Python and browser bindings. Built to make documents LLM-ready.

- Magnitude: 2.3 out of 10 — Steady
- Stars: 23,219 total · +23 stars measured 2026-10-29, 00:07–10:02 UTC, ≈ 48 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Rust · License: MIT · Created: 2026-08-03 · Last push: 2026-10-23
- GitHub: https://github.com/firecrawl/anydoc · Homepage: https://firecrawl.github.io/anydoc/ · Page: https://gitnova.dev/en/r/firecrawl/anydoc

## Useful for

- Convert a .docx or .pptx to Markdown via the CLI for downstream processing
- Embed document conversion into a Python or Node.js pipeline via the bindings
- Add anydoc as an Agent Skill so an agent can read office files

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:07–10:02: 23196 → 23219 stars (+23). This is the change over that interval.
- Estimated end-of-day forecast: about +48 stars, using observed gains and the previous day.
- Over the last two days the pace is 1.6× that of the previous week and a half.
- Top new repositories in the last 4 months: #16.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,504
- Issues and pull requests: 207
- Watchers: 57
- Average over the last week: 31 per day
- Usual pace: 37 per day
- Stars in the last hour (measured): 3
- Latest release: v0.2.4 (2026-08-27)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 36, 77, 73, 29, 31, 31, 24, 46, 45, 22, 45, 38, 53, 33, 31, 29, 23, 31, 27, 38, 26, 27, 23, 25, 19, 30, 26, 34, 37, 23

## Magnitude by day, last 14 days

10-16 2.2, 10-17 2.1, 10-18 2.1, 10-19 2.1, 10-20 2.3, 10-21 2.1, 10-22 2.1, 10-23 2.0, 10-24 2.0, 10-25 2.0, 10-26 2.1, 10-27 2.1, 10-28 2.4, 10-29 2.3

## Spotted in now

- Top new repositories in the last 4 months: #16

## Similar by description

1. **KnifeLemon/Filee** — 5.2 · Peaking · Apps · C# · +689 stars measured 2026-10-29, 00:03–09:58 UTC, ≈ 1,600 by evening
   Free offline file converter in C#: drag files onto a format in a donut menu at your cursor. Supports 244 formats — images, PDF, documents, video, audio, archives, CAD and 3D.
   Full card: https://gitnova.dev/en/r/KnifeLemon/Filee.md
2. **carboneio/carbone-mcp** — 0.0 · Quiet · TypeScript · Not enough measurements today
   Official MCP for Carbone — Document Generation, Document Conversion, and Universal Templating. Generate PDF,DOCX,XLSX,PPTX,CSV,MD,HTML and XML documents from templates+JSON data. Convert Office documents (DOCX, XLSX, PPTX) and HTML to…
   Full card: https://gitnova.dev/en/r/carboneio/carbone-mcp.md
3. **genspark-ai/genoffice** — 3.2 · Steady · Apps · TypeScript · +46 stars measured 2026-10-29, 00:05–10:00 UTC, ≈ 109 by evening
   Open-source office suite with a built-in AI agent: edits real .docx/.xlsx/.pptx, PDF, Markdown and HTML files, converts PDF to Word on-device, runs on macOS, Windows and Linux.
   Full card: https://gitnova.dev/en/r/genspark-ai/genoffice.md
4. **ELY-Open-Source/ElyOffice** — 1.6 · Cooling · Apps · Rust · +7 stars measured 2026-10-29, 00:09–10:06 UTC, ≈ 18 by evening
   A suite of offline-first desktop document apps built in Rust and GPUI: word processing, spreadsheets, presentations, PDF, Markdown and a Git client. Files stay local, with no account or cloud.
   Full card: https://gitnova.dev/en/r/ELY-Open-Source/ElyOffice.md
5. **Joconnell04/blueprint** — 0.0 · Quiet · Python · Not enough measurements today
   Claude Desktop MCP App: plan a workbook or deck on a canvas, approve it, then build the .xlsx or .pptx
   Full card: https://gitnova.dev/en/r/Joconnell04/blueprint.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 10:11 UTC, updated every 30 minutes.