{"slug": "markitdown", "name": "MarkItDown", "category": "terminal", "category_name": "Terminal and shell", "description": "", "recommenders": 6, "commenters": 9, "warners": 0, "score": 6.096, "rising": -1.96, "first": "2025-11-24", "latest": "2026-07-01", "why": "using https://github.com/microsoft/markitdown which I've found to work really well", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 3, "compare": 0, "warn": 0}, "spark": [0, 0, 1, 0, 2, 0, 0, 2, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "using https://github.com/microsoft/markitdown which I've found to work really well", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/microsoft/markitdown", "official_url": "https://github.com/microsoft/markitdown", "pricing": "", "aliases": ["MarkItDown", "markitdown"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 780087425, "item_id": 48755464, "url": "https://news.ycombinator.com/item?id=48755464", "by": "evdubs", "date": "2026-07-01", "stance": "recommend", "quote": "Take a PDF -> run it through MarkItDown [1]", "excerpt": "You don't need to use an online service to do this; you get to avoid spending money on tokens doing it offline. Gemma 4 works perfectly well offline on limited hardware (I have an 8GB video card) and can handle extracting text from image-based PDFs just fine. Take a PDF -> run it through MarkItDown [1], using the OCR plugin if you need (point it to Gemma 4) -> now you can ask Gemma 4 questions about the document. I a", "context": "", "use_case": "PDF to text", "switched_from": "", "story": "Meta Caps Internal AI Token Spending After Costs Approach Billions in 2026"}, {"id": 778699552, "item_id": 48668722, "url": "https://news.ycombinator.com/item?id=48668722", "by": "lostsock", "date": "2026-06-24", "stance": "recommend", "quote": "using https://github.com/microsoft/markitdown which I've found to work really well", "excerpt": "I have a standing instruction for any documents that can't natively be read by a given AI to first be converted into .md using https://github.com/microsoft/markitdown which I've found to work really well", "context": "", "use_case": "converting documents to Markdown", "switched_from": "", "story": "Computer use in Gemini 3.5 Flash"}, {"id": 777979136, "item_id": 48623696, "url": "https://news.ycombinator.com/item?id=48623696", "by": "verdverm", "date": "2026-06-21", "stance": "recommend", "quote": "Microsoft OSS python: https://github.com/microsoft/markitdown", "excerpt": "Native support: https://techcommunity.microsoft.com/blog/onedriveblog/introducing-markdown-support-in-sharepoint-and-onedrive/4512174 Microsoft OSS python: https://github.com/microsoft/markitdown There seem to be many addons that enable this, and pandoc as others have suggested", "context": "", "use_case": "convert Word to Markdown", "switched_from": "", "story": "Ask HN: How should I convert Microsoft Word documents to Markdown?"}, {"id": 756934593, "item_id": 47308412, "url": "https://news.ycombinator.com/item?id=47308412", "by": "albert_e", "date": "2026-03-09", "stance": "recommend", "quote": "Microsoft Markitdown -- that other helpful comments suggested -- seem like two options that might actually work in my case", "excerpt": "I am surprised at such negative responses. I am asking about alternatives to LibreOffice for a reason (stated) Pandoc library and Microsoft Markitdown -- that other helpful comments suggested -- seem like two options that might actually work in my case and I will give them a try. My asking here was fruitful. Running python and using python libraries is allowed on our work pcs but not running arbitrary software and EX", "context": "", "use_case": "Convert documents to Markdown", "switched_from": "", "story": "LibreOffice Writer now supports Markdown"}, {"id": 756791792, "item_id": 47299487, "url": "https://news.ycombinator.com/item?id=47299487", "by": "mrw34", "date": "2026-03-08", "stance": "recommend", "quote": "https://github.com/microsoft/markitdown", "excerpt": "https://github.com/microsoft/markitdown", "context": "", "use_case": "convert Office docs to Markdown", "switched_from": "", "story": "LibreOffice Writer now supports Markdown"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["convert documents to markdown", "pdf to text", "converting documents to markdown", "convert word to markdown", "convert office docs to markdown", "safely converting pdfs to text"], "compared": [{"slug": "pandoc", "name": "Pandoc", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47298885", "title": "LibreOffice Writer now supports Markdown", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48754713", "title": "Meta Caps Internal AI Token Spending After Costs Approach Billions in 2026", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48711681", "title": "Jimmy is a tool to convert your notes from different formats to Markdown", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48662999", "title": "Computer use in Gemini 3.5 Flash", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48622123", "title": "Ask HN: How should I convert Microsoft Word documents to Markdown?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46675030", "title": "How I Became a Quant [pdf]", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 1}, "2025-12": {}, "2026-01": {"neutral": 1, "recommend": 1}, "2026-02": {}, "2026-03": {"recommend": 2}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 2, "neutral": 1}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 780087425, "item_id": 48755464, "url": "https://news.ycombinator.com/item?id=48755464", "by": "evdubs", "date": "2026-07-01", "stance": "recommend", "quote": "Take a PDF -> run it through MarkItDown [1]", "excerpt": "You don't need to use an online service to do this; you get to avoid spending money on tokens doing it offline. Gemma 4 works perfectly well offline on limited hardware (I have an 8GB video card) and can handle extracting text from image-based PDFs just fine. Take a PDF -> run it through MarkItDown [1], using the OCR plugin if you need (point it to Gemma 4) -> now you can ask Gemma 4 questions about the document. I a", "context": "", "use_case": "PDF to text", "switched_from": "", "story": "Meta Caps Internal AI Token Spending After Costs Approach Billions in 2026"}, {"id": 779517328, "item_id": 48719833, "url": "https://news.ycombinator.com/item?id=48719833", "by": "currycurry16", "date": "2026-06-29", "stance": "neutral", "quote": "Related: https://github.com/microsoft/markitdown", "excerpt": "Related: https://github.com/microsoft/markitdown", "context": "", "use_case": "convert documents to Markdown", "switched_from": "", "story": "Jimmy is a tool to convert your notes from different formats to Markdown"}, {"id": 778699552, "item_id": 48668722, "url": "https://news.ycombinator.com/item?id=48668722", "by": "lostsock", "date": "2026-06-24", "stance": "recommend", "quote": "using https://github.com/microsoft/markitdown which I've found to work really well", "excerpt": "I have a standing instruction for any documents that can't natively be read by a given AI to first be converted into .md using https://github.com/microsoft/markitdown which I've found to work really well", "context": "", "use_case": "converting documents to Markdown", "switched_from": "", "story": "Computer use in Gemini 3.5 Flash"}, {"id": 777979136, "item_id": 48623696, "url": "https://news.ycombinator.com/item?id=48623696", "by": "verdverm", "date": "2026-06-21", "stance": "recommend", "quote": "Microsoft OSS python: https://github.com/microsoft/markitdown", "excerpt": "Native support: https://techcommunity.microsoft.com/blog/onedriveblog/introducing-markdown-support-in-sharepoint-and-onedrive/4512174 Microsoft OSS python: https://github.com/microsoft/markitdown There seem to be many addons that enable this, and pandoc as others have suggested", "context": "", "use_case": "convert Word to Markdown", "switched_from": "", "story": "Ask HN: How should I convert Microsoft Word documents to Markdown?"}, {"id": 756934593, "item_id": 47308412, "url": "https://news.ycombinator.com/item?id=47308412", "by": "albert_e", "date": "2026-03-09", "stance": "recommend", "quote": "Microsoft Markitdown -- that other helpful comments suggested -- seem like two options that might actually work in my case", "excerpt": "I am surprised at such negative responses. I am asking about alternatives to LibreOffice for a reason (stated) Pandoc library and Microsoft Markitdown -- that other helpful comments suggested -- seem like two options that might actually work in my case and I will give them a try. My asking here was fruitful. Running python and using python libraries is allowed on our work pcs but not running arbitrary software and EX", "context": "", "use_case": "Convert documents to Markdown", "switched_from": "", "story": "LibreOffice Writer now supports Markdown"}, {"id": 756791792, "item_id": 47299487, "url": "https://news.ycombinator.com/item?id=47299487", "by": "mrw34", "date": "2026-03-08", "stance": "recommend", "quote": "https://github.com/microsoft/markitdown", "excerpt": "https://github.com/microsoft/markitdown", "context": "", "use_case": "convert Office docs to Markdown", "switched_from": "", "story": "LibreOffice Writer now supports Markdown"}, {"id": 747933408, "item_id": 46745838, "url": "https://news.ycombinator.com/item?id=46745838", "by": "nebezb", "date": "2026-01-24", "stance": "recommend", "quote": "I use markitdown[0] religiously.", "excerpt": "I use markitdown[0] religiously. You\u2019ll lose fidelity for anything complex (math equations, images), but it does a great job 95% of the time in my experience. I\u2019m assuming the attack surface is reduced. I invoke it through a docker container. But this might be a misplaced sense of safety. [0] https://github.com/microsoft/markitdown", "context": "", "use_case": "safely converting PDFs to text", "switched_from": "", "story": "How I Became a Quant [pdf]"}, {"id": 745400449, "item_id": 46587528, "url": "https://news.ycombinator.com/item?id=46587528", "by": "kristopolous", "date": "2026-01-12", "stance": "neutral", "quote": "lightpanda url | markitdown (microsoft) | sd (day50 streamdown)", "excerpt": "I've been using it for months now ever since I saw their presentation at GitHub This is a common flow for me lightpanda url | markitdown (microsoft) | sd (day50 streamdown) I even have it as a shell alias, wv(). It's way better than the crusty old lynx and links on sites that need JS. It's solid. Definitely worth a check", "context": "", "use_case": "converting HTML to markdown", "switched_from": "", "story": "Lightpanda migrate DOM implementation to Zig"}, {"id": 736665298, "item_id": 46041581, "url": "https://news.ycombinator.com/item?id=46041581", "by": "smallnest", "date": "2025-11-24", "stance": "neutral", "quote": "calls the `markitdown` Skill to convert the Baidu Baike page", "excerpt": "While Claude Skills offer powerful capabilities, their utility is primarily confined within the Claude environment itself. To leverage these skills within *your own applications*, we need a dedicated integration solution. That's where *[goskills](https://github.com/smallnest/goskills)* comes in. It's a robust parser and execution tool designed for Claude Skills, enabling you to integrate their functionality into popu", "context": "", "use_case": "Document conversion", "switched_from": "", "story": "Integrating Claude Skills into Your Applications with GoSkills"}]}