{"full_name":"microsoft/markitdown","owner":"microsoft","name":"markitdown","url":"https://github.com/microsoft/markitdown","description":"Python tool for converting files and office documents to Markdown.","homepage":"","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/6154722?v=4","created_at":"2024-11-13T19:56:40Z","pushed_at":"2026-11-07T00:14:01Z","metrics":{"stars":194675,"forks":14678,"watchers":591,"issues":694,"prs":1287,"releases":24,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":78},"growth":{"day":{"stars":165,"forks":21,"base_day":"2026-11-09"},"week":{"stars":1115,"forks":158,"base_day":"2026-11-03"}},"history":{"dates":["2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10"],"stars":[189366,189381,189773,189972,190228,190403,190576,190755,191100,191283,191464,191642,191800,191952,192361,192536,192714,192867,193048,193560,193709,194510,194675],"forks":[14056,14055,14118,14133,14130,14152,14162,14183,14224,14244,14258,14284,14302,14326,14376,14391,14409,14429,14451,14520,14543,14657,14678],"watchers":[594,594,593,592,595,592,590,590,589,590,590,592,594,589,590,591,592,588,588,591,591,591,591],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{"weekly":111,"monthly":105,"daily_rate":200,"total":38},"same_owner":[{"full_name":"microsoft/vscode","name":"vscode","boards":{"daily_rate":199,"total":36}},{"full_name":"microsoft/PowerToys","name":"PowerToys","boards":{"total":81}},{"full_name":"microsoft/generative-ai-for-beginners","name":"generative-ai-for-beginners","boards":{"total":97}},{"full_name":"microsoft/TypeScript","name":"TypeScript","boards":{"total":118}},{"full_name":"microsoft/terminal","name":"terminal","boards":{"total":132}},{"full_name":"microsoft/playwright","name":"playwright","boards":{"total":144}},{"full_name":"microsoft/Web-Dev-For-Beginners","name":"Web-Dev-For-Beginners","boards":{"total":155}},{"full_name":"microsoft/ML-For-Beginners","name":"ML-For-Beginners","boards":{"total":172}},{"full_name":"microsoft/AI-For-Beginners","name":"AI-For-Beginners","boards":{}},{"full_name":"microsoft/AirSim","name":"AirSim","boards":{}},{"full_name":"microsoft/BitNet","name":"BitNet","boards":{}},{"full_name":"microsoft/Bringing-Old-Photos-Back-to-Life","name":"Bringing-Old-Photos-Back-to-Life","boards":{}},{"full_name":"microsoft/CNTK","name":"CNTK","boards":{}},{"full_name":"microsoft/Data-Science-For-Beginners","name":"Data-Science-For-Beginners","boards":{}},{"full_name":"microsoft/FluidFramework","name":"FluidFramework","boards":{}},{"full_name":"microsoft/IoT-For-Beginners","name":"IoT-For-Beginners","boards":{}},{"full_name":"microsoft/MMdnn","name":"MMdnn","boards":{}},{"full_name":"microsoft/Ontology-Playground","name":"Ontology-Playground","boards":{}},{"full_name":"microsoft/RD-Agent","name":"RD-Agent","boards":{}},{"full_name":"microsoft/SandDance","name":"SandDance","boards":{}}],"issues":[{"number":12,"title":"LLM Integration","comments":17,"created_at":"2024-12-13T19:38:10Z"},{"number":23,"title":"Support for .doc extensions","comments":15,"created_at":"2024-12-14T14:42:25Z"},{"number":1282,"title":"DocxConverter threw KeyError with message: 'w:ilvl'","comments":14,"created_at":"2025-06-03T08:18:33Z"},{"number":114,"title":"图片无法转换","comments":14,"created_at":"2024-12-18T05:11:02Z"},{"number":1234,"title":"[Feature Request] Magika Dependency Optional","comments":13,"created_at":"2025-05-04T16:37:37Z"},{"number":204,"title":"Path to markitdown","comments":13,"created_at":"2024-12-23T02:09:19Z"},{"number":41,"title":"Preserve tables, titles (structure) of PDF documents","comments":12,"created_at":"2024-12-15T19:05:30Z"},{"number":316,"title":"Document Intelligence is not working","comments":11,"created_at":"2025-02-04T23:40:25Z"}],"discussions":[{"number":2789,"title":"Proposal: optional source maps from Markdown back to document locations","comments":0,"category":"Ideas","created_at":"2026-10-29T15:09:59Z"},{"number":2715,"title":"MarkItDown included in AgentManager's tool catalog","comments":0,"category":"Show and tell","created_at":"2026-10-18T09:14:09Z"},{"number":2669,"title":"docx-repro: shrink DOCX conversion bug reports while preserving the exact symptom","comments":0,"category":"Show and tell","created_at":"2026-10-07T13:32:04Z"},{"number":2593,"title":"Capping what one batch of llm_client image captions can cost","comments":0,"category":"Show and tell","created_at":"2026-10-03T20:23:40Z"},{"number":2590,"title":"browser Claude","comments":1,"category":"Q&A","created_at":"2026-10-03T10:16:19Z"},{"number":2548,"title":"Install as Claude Skill?","comments":3,"category":"Q&A","created_at":"2026-09-23T17:52:44Z"},{"number":2471,"title":"Running MarkItDown as a standing REST service (not just a CLI call)","comments":0,"category":"Show and tell","created_at":"2026-09-12T03:02:24Z"},{"number":2397,"title":"Markitdown MCP Plugin for VSCode","comments":2,"category":"Q&A","created_at":"2026-09-07T13:30:10Z"}],"latest_release":{"name":"Version 0.1.9","tag":"v0.1.9","published_at":"2026-10-21T19:40:32Z","body":"## What's Changed\r\n* increase chunk size from 512 bytes to 64 KB for HTTP response reading by @YasirAlibrahem in https://github.com/microsoft/markitdown/pull/1511\r\n* fix(wikipedia): accept mobile (m.wikipedia.org) URLs by @GopalGB in https://github.com/microsoft/markitdown/pull/1850\r\n* fix: handle None sys.stdout.encoding in CLI output by @octo-patch in https://github.com/microsoft/markitdown/pull/1656\r\n* Add language parameter for the audio transcription by @hchmch in https://github.com/microsoft/markitdown/pull/1295\r\n* Perf: Optimize non-seekable stream buffering using shutil.copyfileobj by @YasirAlibrahem in https://github.com/microsoft/markitdown/pull/1510\r\n* Use frozenset for OMML direct tag lookup by @Amitanand983 in https://github.com/microsoft/markitdown/pull/1919\r\n* fix(wikipedia): drop the site suffix from italicised titles by @macjayz in https://github.com/microsoft/markitdown/pull/2458\r\n* Consolidate tests by format and strengthen regression coverage by @afourney in https://github.com/microsoft/markitdown/pull/2579\r\n* Replace local parser mocks with real conversion fixtures by @afourney in https://github.com/microsoft/markitdown/pull/2586\r\n* Test real installed OCR plugin discovery by @afourney in https://github.com/microsoft/markitdown/pull/2588\r\n* Test real CLI file-type parsing and CU result formatting by @afourney in https://github.com/microsoft/markitdown/pull/2592\r\n* Test PowerPoint missing text with real fixtures and shared vectors by @afourney in https://github.com/microsoft/markitdown/pull/2594\r\n* Test MCP input errors with real conversions by @afourney in https://github.com/microsoft/markitdown/pull/2597\r\n* Restore JSON regression coverage for late non-ASCII text by @afourney in https://github.com/microsoft/markitdown/pull/2601\r\n* Bump the magika dependency by @afourney in https://github.com/microsoft/markitdown/pull/2722\r\n* Bump Mammoth dependency to >=1.12.2,<2 by @afourney in https://github.com/microsoft/markitdown/pull/2729\r\n* Require certifi>=2026.10.19 for updated CA trust by @afourney in https://github.com/microsoft/markitdown/pull/2730\r\n* Update Black, Pillow, and Windows ARM Cryptography baselines by @afourney in https://github.com/microsoft/markitdown/pull/2731\r\n\r\n## New Contributors\r\n* @YasirAlibrahem made their first contribution in https://github.com/microsoft/markitdown/pull/1511\r\n* @GopalGB made their first contribution in https://github.com/microsoft/markitdown/pull/1850\r\n* @octo-patch made their first contribution in https://github.com/microsoft/markitdown/pull/1656\r\n* @hchmch made their first contribution in https://github.com/microsoft/markitdown/pull/1295\r\n* @Amitanand983 made their first contribution in https://github.com/microsoft/markitdown/pull/1919\r\n\r\n**Full Changelog**: https://github.com/microsoft/markitdown/compare/v0.1.8...v0.1.9"},"readme":true,"readme_zh":false,"news":[{"title":"MarkItDown: Python tool for converting files and office documents to Markdown","url":"https://github.com/microsoft/markitdown","hn":"https://news.ycombinator.com/item?id=42410803","source":"Hacker News","lang":"en","date":"2024-12-13","points":329,"comments":81},{"title":"Python tool for converting files and office documents to Markdown","url":"https://github.com/microsoft/markitdown","hn":"https://news.ycombinator.com/item?id=48489166","source":"Hacker News","lang":"en","date":"2026-06-11","points":6,"comments":0},{"title":"Microsoft Markitdown jumped on the MCP bandwagon","url":"https://news.ycombinator.com/item?id=43760013","hn":"https://news.ycombinator.com/item?id=43760013","source":"Hacker News","lang":"en","date":"2025-04-22","points":2,"comments":0},{"title":"Microsoft Wakeup: You Have a Killer Static Site Generator!","url":"https://news.ycombinator.com/item?id=18824548","hn":"https://news.ycombinator.com/item?id=18824548","source":"Hacker News","lang":"en","date":"2019-01-04","points":2,"comments":1},{"title":"Markitdown：微軟開源工具，一鍵將 Office 文件轉 Markdown","url":"https://www.techritual.com/2026/08/09/529138/","source":"techritual","lang":"zh","date":"2026-08-08"},{"title":"MarkItDown: Microsofts Tool senkt Token-Verbrauch um 70 Prozent","url":"https://www.ad-hoc-news.de/wissenschaft/markitdown-microsofts-tool-senkt-token-verbrauch-um-70-prozent/69532016","source":"ad-hoc-news","lang":"en","date":"2026-06-13"},{"title":"微軟開源超好用工具 MarkItDown：把 PDF、Word、PPT 一鍵轉成 AI 看得懂的 Markdown","url":"https://www.kocpc.com.tw/archives/638475","source":"電腦王阿達","lang":"zh","date":"2026-04-09"},{"title":"Microsoft MarkItDown Guide: Install, Use, Supported Formats, and Limitations","url":"https://www.remio.ai/post/microsoft-markitdown-open-source-tool-for-markdown-conversion-and-ai-document-parsing","source":"remio.ai","lang":"en","date":"2025-09-15"},{"title":"MarkItDown: Microsoft’s open-source tool for Markdown conversion","url":"https://www.infoworld.com/article/3963991/markitdown-microsofts-open-source-tool-for-markdown-conversion.html","source":"InfoWorld","lang":"en","date":"2025-04-24"},{"title":"微软开源新工具 MarkItDown，Office 文件轻松转换为Markdown格式","url":"https://news.qq.com/rain/a/20241217A066R300","source":"腾讯网","lang":"zh","date":"2024-12-17"},{"title":"微软发布MarkItDown开源Python库 兼容多种文件格式","url":"https://finance.sina.com.cn/tech/roll/2024-12-17/doc-inczukxm4786609.shtml","source":"新浪网","lang":"zh","date":"2024-12-17"},{"title":"MarkItDown - Convert all your documents to Markdown super easily","url":"https://korben.info/en/markitdown-convert-documents-to-markdown.html","source":"korben","lang":"en","date":"2024-12-14"},{"title":"2026.09.18开源项目日榜：STM32、MarkItDown与蚁群算法热点速览","url":"https://news.google.com/rss/articles/CBMiXkFVX3lxTE12MlVkaUxvaDJsOWstVHBwZXpJd2kyM3kyaF9YSkw1a0NZcXpCcUxfR1NNTXQxMTRLbVBNdjRZVEdiNXl6SDJCOWotMmJScDBYdUc0OUR3LWdEZzFBbUE?oc=5","source":"CSDN","lang":"zh","date":"2026-11-09"},{"title":"GitHub热榜8大项目深度拆解：从AI工具到嵌入式与算法","url":"https://news.google.com/rss/articles/CBMiX0FVX3lxTFBnRWR2NTlPZ1Flb0tBZmVDUWRBRzZEbXdhNURvMVo5MVdxZG5OT1NkQnJVU3haSVAxcURiU3IxbllRWHlyU0dzY2xDcHV1M3lxZlI2YTI3SUY2QVhNSThj?oc=5","source":"CSDN","lang":"zh","date":"2026-11-06"},{"title":"一周GitHub精选：6个值得动手的开源项目，从AI到嵌入式全覆盖","url":"https://news.google.com/rss/articles/CBMiX0FVX3lxTE10czRQRnZHc210UkNaX1BtNlI5dTBYS245NWJRcjljQUFfaWxKcWNoWWN3eHp0Q3pmSTFndnVuR0JpVTNYalRlMVVnS0J4d2U4cURRcjJ5TEQ5bjBndmRF?oc=5","source":"CSDN","lang":"zh","date":"2026-11-05"},{"title":"New MCP Security Flaws: Kubectl-mcp-server, Archon OS, and MarkItDown Vulnerabilities","url":"https://news.google.com/rss/articles/CBMisgFBVV95cUxNT19qMjk5eHY1cVVkZjR2QzNnMC1IZFBib1FaWURKUEV5eXl0Nm13RTlOWFE4U21ZYnhZN1F3akwxMHpVOFIwdGpYSTUtcC0xXzdLamN1dHNaN0xzUG1HUHZndk9NU1AyQkNJMG1EemR3VTVBQUlRR0lua083aHhnR2FOM0V3UFlLUmV5NjBOUkFSNi1YNDVpbkFZbGx6cklaLXdGbW5SbGFKcmRWR084Y09R?oc=5","source":"OX Security","lang":"en","date":"2026-05-12"},{"title":"Markdown 已死，HTML 当立？","url":"https://news.google.com/rss/articles/CBMiVkFVX3lxTE1VcGM3MnVud1djNXUwdVFrSXFHWUpnRGNCc0p2NXUzbWVCdjJsR0pqVFlHUkZURW0zZXgxZzJldGtEWUdSdzF1WnNKUzhYbTZMaW9uN2tR?oc=5","source":"QQ News","lang":"zh","date":"2026-05-12"},{"title":"12 Python Libraries You Need to Try in 2026","url":"https://news.google.com/rss/articles/CBMieEFVX3lxTE1hZG1FRXNTTE5INC1WM0ZxVVRkT3B0R2FDOEp0YzhQSDZSMkY1bUQ3Zjc5V2QyMGY2cEwxUEgyQ0I1cjZoSUpEdU5keW82TVpoSEV6TU5QNlVham0yUE5ORnRtMmpFR0EwRjRlbDZ4WHFpR3pYandIaA?oc=5","source":"KDnuggets","lang":"en","date":"2026-02-13"},{"title":"Microsoft MarkItDown Guide: Install, Use & Limitations","url":"https://news.google.com/rss/articles/CBMisAFBVV95cUxPNTctTEY2RWxzN0U2YnFkbEI5U1lLQmtKMDAwS2o3SmNhdU56MkY5OTR3X1M0YnlFRVhPaGpmbTNfNmFZbS14OFpzNU1HN2ktc2hfVE82cFpZZjRoUkFjNnBpWFMtbUd3dlRSaHRMYVpuQjl1QldXMW8xZmNLZE5JVU1vUmdCQ2xqVnBBdkpQWUpQcTBycVh1a0dGOFBpR2Y1eWtKUEFoQTRTZGlvRVdFaQ?oc=5","source":"remio","lang":"en","date":"2025-09-15"},{"title":"微软偷偷上线一款MCP神器，可让Office文件秒变Markdown！","url":"https://news.google.com/rss/articles/CBMicEFVX3lxTE5Nck5xeTR1SW1JQ0Z3ZmJRY1BEMy1vRWxwMmkwQnFQOVUzaHJkUjNuRDlHYTJBaWE4Vk5hNTN4czM4cmhxVXFneHBITFVVcDE1WkRoRUZwMnRMaWVXNjhCUGxCdTcwQWlCamQtV0ZrSkE?oc=5","source":"53AI","lang":"zh","date":"2025-04-20"},{"title":"6大RAG知识库PDF文档处理工具对比！","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE94UVczY0dJS2lDS2dBQUtRaVNjM2pDZlM4TS1TcVpXUmNodE44TkpsQW5pTUU2ZlRfNjNmVk5CWmR4U3BxNzc0ZA?oc=5","source":"智源社区","lang":"zh","date":"2025-03-04"},{"title":"微软开源Markdown工具爆了：支持Office文档，可接多模态LLM直出报告","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTFBUTVk2T1k1TVVoUHI1azJodjJ3NmhKVnRXaHBRU3pxTU1SMmd3azNmUDQ5TnRIZmljWEttRy1jTlBLYVgxcnNZTQ?oc=5","source":"凤凰网","lang":"zh","date":"2025-01-20"},{"title":"Microsoft MarkItDown: Everything You Need to Know","url":"https://news.google.com/rss/articles/CBMigAFBVV95cUxOZy1hd3IyQ3pSVVROb254cTAwYU84aHZFdG1OYUxYclVFeDE1bTl1NVhLdC16d0VnY3JJZEZjWWxqT2NBekRrWXhwOTd3enJKYVZCNGx3amExRTJ1ck5RS19yZFBObTF4SUVEakJZcGlUdEN4UjNial9rY1Q5NmVmQQ?oc=5","source":"Substack","lang":"en","date":"2024-12-24"}],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}