MarkItDown by Microsoft

Shares rank 6 of 8 document parsers by recommenders

People recommend it for converting documents to Markdown, especially as clean raw text for LLM agents, and say it works well most of the time.

7 people gave an opinion

Each figure is one person. RecommendsCriticizes

The same three rules apply to every product, and the badge can’t be bought. How the badge works

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Each mark is one comment

Clean Markdown output for LLM agents
“which is not only token efficient but also llms are pretty good at creating hierarchies from markdown”
Comment from 22 Dec 2025 in “A guide to local coding models”
“markitdown is solid when you mostly want raw text out for agents”
Comment from 12 Apr 2026 in “Show HN: MarkitMe, Turn Anything into Markdown”
Works well most of the time
“it does a great job 95% of the time in my experience”
Comment from 24 Jan 2026 in “How I Became a Quant [pdf]”
“which I've found to work really well”
Comment from 25 Jun 2026 in “Computer use in Gemini 3.5 Flash”

5 of the 7 comments that mention it, newest first. Each links to the original comment.

“which I've found to work really well”

RecommendsComment from 25 Jun 2026 in “Computer use in Gemini 3.5 Flash”

“markitdown is solid when you mostly want raw text out for agents”

RecommendsComment from 12 Apr 2026 in “Show HN: MarkitMe, Turn Anything into Markdown”

“Anything that can run locally instead of uploading potentially sensitive stuff to random websites.”

RecommendsComment from 8 Mar 2026 in “LibreOffice Writer now supports Markdown”

“it does a great job 95% of the time in my experience”

RecommendsComment from 24 Jan 2026 in “How I Became a Quant [pdf]”

“which is not only token efficient but also llms are pretty good at creating hierarchies from markdown”

RecommendsComment from 22 Dec 2025 in “A guide to local coding models”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.

Product	Recommend	Criticize	Approval	Months	Owned	Badge
Pandoc	142	28	84%	13	10 yrs6 owners	Approved
Tesseract OCR	32	28	53%	12	—	—
Docling	19	4	83%	10	—	Approved
Mozilla Readability	10	1	91%	6	—	Approved
MarkItDown by MicrosoftThis page	7	0	100%	6	—	—