{"slug": "i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally", "title": "I built a Mac app that turns document folders into RAG-ready Markdown — locally", "summary": "A developer has released Milldown, a native macOS app that converts PDFs, Office documents, spreadsheets, web pages and other formats into clean Markdown entirely on the local machine for LLM and RAG pipelines. The app wraps Microsoft's open-source MarkItDown engine and adds OCR, folder mirroring, watch folders, chunk export, token accounting and a CLI, with published benchmarks showing 72–95% fewer tokens for web pages and 71–84% fewer for PDFs versus raw inputs. It is free for 14 days, then $39 for a perpetual licence covering up to three Macs, or $249 for a 10-seat team licence.", "body_md": "I kept hitting the same wall: I have a folder of PDFs, Word files and spreadsheets, and I want them as clean Markdown so I can feed them to an LLM or a RAG pipeline. Every tool I tried either uploaded my documents to someone's server, or gave me Markdown I had to clean up by hand.\n\nSo I built **Milldown**, a native macOS app that does the conversion entirely on your machine. I'm the developer — this is a \"here's the thing I made\" post, and I'll happily answer anything technical in the comments.\n\nDrop in files, a URL, or a whole folder. Milldown converts them and shows you the Markdown side by side with a rendered preview, so you can check the output before it goes anywhere near your pipeline.\n\nThe bits that matter if you're building with this:\n\n`milldown://` URL scheme, so the same conversion you just did by hand can go in a script or a Shortcut.\nOn that last point, I published [the benchmark](https://milldown.app/benchmarks) rather than asking you to take a number on faith: a pinned corpus, defined baselines, committed results. Measured there — web pages 72–95% fewer tokens than raw HTML, PDFs 71–84% fewer than attaching the PDF natively. Spreadsheets go the other way: CSV beats a Markdown pipe table by 12–29%, so that's what it recommends for them.\n\nPDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, RSS/Atom, EPUB, ZIP, Jupyter notebooks, Outlook `.msg`, text/Markdown, JPEG/PNG — plus web pages, Wikipedia articles and YouTube transcripts by URL.\n\nUnder the hood conversion is powered by Microsoft's open-source [MarkItDown](https://github.com/microsoft/markitdown) engine (MIT), bundled inside the app. I'm not affiliated with Microsoft — Milldown is the native Mac app around it: the OCR path, folder mirroring, watch folders, chunk export, token accounting and the CLI.\n\nFree for 14 days with every feature unlocked and no account required. After that it's a $39 perpetual licence for up to 3 Macs, or $249 for a 10-seat team licence — 12 months of updates included, renewals optional, nothing billed automatically, 14-day money-back guarantee.\n\nIf you're doing local RAG prep on a Mac, I'd genuinely like to know which provenance fields you keep on your chunks — source path, page, heading path, extraction time — and whether you put them in JSONL metadata, front matter, or both. That's the part I'm least sure I've got right.", "url": "https://wpnews.pro/news/i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally", "canonical_source": "https://dev.to/alan_scales_f5903e50d013d/milldownapp-full-markitdown-wrapper-1oj9", "published_at": "2026-09-14 17:00:24+00:00", "updated_at": "2026-09-14 17:26:10.262572+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "developer-tools", "large-language-models", "mlops"], "entities": ["Milldown", "Microsoft", "MarkItDown", "macOS"], "alternates": {"html": "https://wpnews.pro/news/i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally", "markdown": "https://wpnews.pro/news/i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally.md", "text": "https://wpnews.pro/news/i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally.txt", "jsonld": "https://wpnews.pro/news/i-built-a-mac-app-that-turns-document-folders-into-rag-ready-markdown-locally.jsonld"}}