bobnarizes

A clear sign for me is always the use of long em dashes ⸺

(+ Germany and Mexico)

Building https://floxtop.com, a native Mac app that organizes and rename your files with reliable AI.

It looks inside each file to see what it’s about, then suggest the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It works in 50 languages (including English, German, French, Spanish, Swedish) and with images (OCR and object recognition), PDFs, Microsoft Office, ePubs, text, Markdown, and many other file types.

For messy folders anywhere on the Mac, Floxtop can help.

Building https://floxtop.com, a native Mac app that organizes your files with reliable AI.

It looks inside each file to see what it’s about, then suggest the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It works in 50 languages (including English, German, French, Spanish, Swedish) and with images (OCR and object recognition), PDFs, Microsoft Office, ePubs, text, Markdown, and many other file types.

Next, rename files based on their content (e.g. 123023dfawjher.pdf → finance_chart_fy26.pdf).

For messy folders anywhere on the Mac, Floxtop can help.

Floxtop never creates or changes your folder structure. You decide where files should live by creating categories. A category has two things:

1. A short description of what kind of files belong there

2. A specific folder on your Mac as the destination

When you drop unsorted files into Floxtop, it looks inside each file, understands what it’s about, and compares it with your categories. Instead of picking a single place, Floxtop suggests the five most likely destinations, ordered by confidence.

Nothing happens automatically:

- Files are never moved on their own

- You review the suggestions and decide what gets moved

- If a file doesn’t clearly belong anywhere, it stays untouched

Floxtop helps you decide where things belong — the final action is always yours.

Building https://floxtop.com, a native Mac app that organizes your files.

It looks inside each file to see what it’s about, then moves it to the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It works in 50 languages (including English, German, French, Spanish, Swedish) and with images (OCR and object recognition), PDFs, Microsoft Office, ePubs, text, Markdown, and many other file types.

For messy folders anywhere on the Mac, Floxtop can help.

I’ve seen a huge advantage in running everything fully local and private. Not sure if that fits your use case, though. Nearly 90% of Floxtop users choose the app mainly for that privacy focus.

Not Apple Foundation Models — unfortunately they’re not capable enough (yet) for understanding content and matching it to folders.

I’m using SBERT-style embedding models for the semantic matching, which works very well in practice.

For non-text content, the app also analyzes images (OCR + object recognition) using Apple’s Vision framework. That part is surprisingly powerful, especially on Apple Silicon.

I need to do something for images that are already classified/tagged via FastVLM

What’s the concrete use case you’re targeting with this?

Side project: A native macOS app in Swift that runs locally and uses AI to clean and organize files by moving them into the best-matching folders. No backend or accounts. https://floxtop.com

Full-time: C++ work on nearby connectivity (bluetooth) for embedded / industrial devices (factory equipment). Deep stack, hardware constraints, long lifecycles, high reliability.

Non-web work feels very different: stronger constraints, slower but deliberate releases, and bugs are much more expensive. There’s a lot of interesting software being built far away from HTTP and browsers.

There is no automatic execution — nothing is moved without your confirmation.

Floxtop suggests the top 5 destination folders where a file could best belong. You stay fully in control: you can choose one of the suggestions, move files individually or in bulk (Move All), or select a completely custom folder location at any time.

If you change your mind, you can Undo per file or use Undo All to revert the entire operation.

Building https://floxtop.com, a native Mac app that organizes your files.

It looks inside each file to see what it’s about, then moves it to the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It works in 50 languages (including English, German, French, Spanish, Swedish) and with images (OCR and object recognition), PDFs, Microsoft Office, ePubs, text, Markdown, and many other file types.

If you have messy folders anywhere on your Mac, Floxtop can help.

HUMAN

A highly social, relatively hairless bipedal ape that was once a nomadic hunter-gatherer, but has adapted to create websites. :)

Hi, thanks for the feedback.

1. A Homebrew option isn’t available yet, but it’s something I’m open to exploring. Homebrew doesn’t currently support payments or license handling for paid apps, so Floxtop doesn’t fit perfectly into their workflow. For now, it’s available via direct download from the website.

2. Multi-language support. Yes — I’m actively working on this. Which languages would be most important for you? That helps me prioritize.

3. Moving files to mounted folders (e.g., Google Drive) Great suggestion. I’ll look into this, as supporting mounted cloud folders could be very helpful for many users.

Hi HN, Floxtop is a native macOS app that organizes files and images by their content — not just their names. It runs fully offline on Apple Silicon, with no servers, no cloud, and no data leaving your machine.

Problem: My Downloads and Desktop folders would fill up with PDFs, screenshots, and random files, making cleanup and finding the right file frustrating and time-consuming. Solution: Floxtop uses Sentence Transformers (SBERT) to embed document text and metadata, plus OCR and object recognition to read images. It groups and classifies files by semantic similarity — all locally, so your sensitive files (finance, medical, personal, etc.) stay private.

Current version: Supports 30+ file types including images, Office documents (Word, Excel, PowerPoint), PDFs, EPUBs, Markdown, CSV, and more. Parsing and classifying 50 files takes around 17 seconds. It integrates with Finder (right-click > Organize with Floxtop), Quick Look + thumbnails, and includes keyboard shortcuts for a fast workflow. Currently, Intel Macs are not supported and it only works with English-language files.

I launched an early beta ~3 months ago, Fallinorg (https://news.ycombinator.com/item?id=44932375), and have since built out more features based on user feedback. I’d love your feedback on classification workflows, missing features, pricing, usability, and potential bulk operations or integrations. Happy to answer questions and share implementation details!

Free version here - requires macOS 15+ with Apple Silicon: https://github.com/taranntell/fallinorg/releases/download/1....

Demo video: https://floxtop.com/assets/demo.mp4

This is cool! I’ve added these to the backlog—I also think tagging with Finder tags/xattrs is a great feature. Thanks a lot for sharing your ideas!

If you want to stay updated when these features are ready, feel free to subscribe to the newsletter.

Correct — right now Floxtop classifies images based on text only. It does not yet classify based on visual objects. If automatic object-based sorting (e.g. detecting pets, buildings, etc.) would be useful for you, I’d be interested to hear your use case.

Regarding privacy: everything runs locally on your Mac. No files or metadata are uploaded anywhere. The only network request is from Sparkle to check for updates. If you prefer, you can disable update checks and Floxtop will have zero network activity.

If you have questions or want to share feedback, you can reach me anytime at floxtop@proton.me.

Building https://floxtop.com/, a Mac app that organizes your files and images.

It looks inside each file to see what it’s about, then moves it to the right folder with a single click. Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It already works with images, Office (Word, Excel, PowerPoint) PDFs, ePubs, text, Markdown, and many other file types (30+) in English. Next I’m adding multi-language support.

If you have messy folders anywhere on your Mac, Floxtop can help.

Try it for free - requires macOS 14+ with Apple Silicon: https://github.com/taranntell/fallinorg/releases/download/1....

Thanks for your interest! Currently, Floxtop is not available on the Mac App Store. I’m considering it for the future, but the high cut Apple takes makes it challenging for an independent app like this.

Out of curiosity, is your preference for the App Store mainly convenience (updates, trust, purchasing), or something else?

If you’d like to be notified when this feature becomes available, you can subscribe to our newsletter — it’s linked in the footer of our website or by sending an email to floxtop at proton.me

Hi HN, Floxtop is a native macOS app that organizes files and images by their content — not just their names. It runs fully offline on Apple Silicon, with no servers, no cloud, and no data leaving your machine.

Problem: My Downloads and Desktop folders would fill up with PDFs, screenshots, and random files, making cleanup and finding the right file frustrating and time-consuming.

Solution: Floxtop uses Sentence Transformers (SBERT) to embed document text and metadata, plus OCR to read images. It groups and classifies files by semantic similarity — all locally, so your sensitive files (finance, medical, personal, etc.) stay private.

Current version: Supports 30+ file types including images (with OCR), Office documents (Word, Excel, PowerPoint), PDFs, EPUBs, Markdown, CSV, and more. Parsing and classifying 50 files takes around 17 seconds. It integrates with Finder (right-click > Organize with Floxtop), Quick Look + thumbnails, and includes keyboard shortcuts for a fast workflow. Currently, Intel Macs are not supported and it only works with English-language files.

I launched an early beta ~3 months ago, Fallinorg (https://news.ycombinator.com/item?id=44932375), and have since built out more features based on user feedback.

I’d love your feedback on classification workflows, missing features, pricing, usability, and potential bulk operations or integrations.

Happy to answer questions and share implementation details!

Free version here - requires macOS 14+ with Apple Silicon: https://github.com/taranntell/fallinorg/releases/download/1....

Demo video: https://floxtop.com/assets/demo.mp4

Building https://fallinorg.com/, a Mac app that organizes your files.

It looks inside each file to see what it’s about, then moves it to the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It already works with PDFs, ePubs, text, Markdown, and many other file types. Next I’m adding Microsoft Office and iWork support.

If you have messy folders anywhere on your Mac, Fallinorg can help.

Thanks Jon, Custom categories are available starting with version 3.0 beta. To add one, open Fallinorg Settings → Add New Category. Then enter a name, description with keywords or sample sentences, and make sure the destination folder is set correctly.

Could you please check in the About section which version of the app you’re running?

Glad it looks useful! Downloads, Desktop folders get messy fast, so it’s perfect for a first clean-up.

How do you usually decide where each file goes in your Johnny Decimal system? I’d love to hear your workflow. Thank you :)

Thanks for sharing, jonpurdy — I know how fast that backlog can build up!

Most tools I’ve seen (like Sparkle) sort by file name, but that only works if names are clear. Fallinorg looks inside the file itself, so it understands what the content is about before sorting. I haven’t found another Mac app doing that.

Curious — if Fallinorg could automatically handle your ~/Downloads/yyyy-mm folders each month, would that take care of the backlog for you?

Thanks so much for your thoughtful comment and support, Brajeshwar — it really means a lot.

You’re right, Fallinorg currently only supports Apple Silicon Macs. The main reason is that the M-series chips have neural engines and very high memory bandwidth, which makes the AI models run fast and efficiently. On Intel Macs the performance just isn’t the same, but I do want to explore ways to bring a great experience there too. If you’d prefer a refund in the meantime, just let me know and I’ll send it right away — no worries at all.

Also, thank you for pointing out the email confirmation — I’ll definitely add that.

I noticed you mentioned using Hazel for years and building up muscle memory with rules. Right now, Fallinorg is built around content-based AI classification rather than rules. But rules can give a lot of precision and flexibility. Could you share what kind of rules or workflows you relied on most with Hazel? That would help me understand how people like you used it, and how Fallinorg might evolve to cover those use cases better.

Again, really appreciate your support and feedback.

Building https://fallinorg.com/, a Mac app that organizes your files.

It looks inside each file to see what it’s about, then moves it to the right folder for you.

Everything happens on your Mac, so nothing leaves your computer. No clouds, no servers.

It already works with PDFs, text, Markdown, and many other file types. Next I’m adding ePub, and later Microsoft Office and iWork support.

If you have messy folders anywhere on your Mac, Fallinorg can help.

Hi John2022,

Me again, thank you very much for testing Fallinorg and letting me know about the crash. Since I don’t see it on my machine, could you help me by sending the crash report?

You can find it here: - Open Console.app → “Crash Reports” → look for a file starting with Fallinorg (it will end with .ips). - Or check in this folder: ~/Library/Logs/DiagnosticReports/.

If you send me the latest .ips file (fallinorg@proton.me), it will help me understand exactly what’s happening and fix it quickly.

Really appreciate your help!

Thanks for reporting this John2022! As mdaniel mention, please file an issue on GitHub so it’s tracked and others can see updates or add details. That way I can fix it faster.

Thank you very much berkesquires! I really appreciate!

Good catch — I’ve fixed the typo and I’m sorry for the oversight. Details matter, especially when trust is involved. Thanks for pointing it out!

Thanks for pointing this out mdaniel & woadwarrior01 — reducing the footprint is definitely on my radar and something I’m actively working on. I actually started with CoreML but switched to ONNX after running into some issues.

That said, it’s kind of amazing that we can run models of ~90 MB this efficiently on our devices today — the performance has been really encouraging. Appreciate the feedback!