# microsoft/markitdown

> A Python utility from Microsoft for converting PDFs, Office documents, images, audio, HTML, and other formats to Markdown, aimed at LLM and text-analysis pipelines. It preserves document structure (headings, lists, tables, links) and is token-efficient.

- Magnitude: 3.2 out of 10 — Steady
- Stars: 190,827 total · +49 stars measured 2026-10-18, 00:22–10:25 UTC, ≈ 127 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2024-11-13 · Last push: 2026-10-04
- GitHub: https://github.com/microsoft/markitdown · Page: https://gitnova.dev/en/r/microsoft/markitdown

## Useful for

- Convert a PDF to Markdown for LLM context
- Extract text and structure from Word/Excel/PPT via CLI
- Enable OCR of images inside PDFs with markitdown-ocr and OpenAI

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 00:22–10:25: 190778 → 190827 stars (+49). This is the change over that interval.
- Estimated end-of-day forecast: about +127 stars, using observed gains and the previous day.
- About 18 forks a day — people are taking the code.

## 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: 14,193
- Issues and pull requests: 1,851
- Watchers: 589
- Average over the last week: 200 per day
- Usual pace: 219 per day
- Latest release: v0.1.8 (2026-09-21)

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

2026-10-01 … 2026-10-30: 136, 184, 167, 276, 251, 192, 212, 247, 178, 170, 235, 234, 263, 220, 179, 216, 160, 29, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-30 3.1, 10-01 3.0, 10-07 3.3, 10-08 4.0, 10-09 3.7, 10-10 3.5, 10-11 4.0, 10-12 3.9, 10-13 3.7, 10-14 4.0, 10-15 3.7, 10-16 3.4, 10-17 4.0, 10-18 3.4

---

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 2026-10-18 10:33 UTC, updated every 30 minutes.