Even without changing one byte of the actual binary they could get pretty far by just evicting all the test files for those packages they're including. And, related to that, it seems that dist-info/RECORD ends up at 1,050,544 because the onnx folks decided it was important that they cryptographically sign all those test data files they're choosing to ship :-/
Hi HN,
Fallinorg is a local macOS app that organizes files by their meaning, not just their name or type.
Problem: My Downloads and Desktop folders kept filling up with cryptically named, duplicate, or unrelated files. Over time, cleaning up and finding the right file became a pain.
Solution: It uses Sentence Transformers (SBERT) to understand the content and context of files, then automatically groups them. It runs fully offline, so you can safely classify sensitive files (finance, medical, personal, etc.). On Apple Silicon, it parses, tokenizes, and categorizes a file in about ~1.2 seconds.
Current version: Supports .txt and .pdf files in English; I’m working on adding more formats and languages.
Looking for feedback on: Classification accuracy, speed, pricing ideas, and potential bulk operations or integrations.
I first launched a few weeks ago and have been rapidly adding features based on early feedback. Happy to answer questions and share implementation details.
Given that this is a Mac app, have you considered taking advantage of the considerable amount of metadata for files (sometimes including full text content) made available by QuickLook? It could extend functionality for many file formats without requiring the app to be able to parse them.
> Over time, cleaning up and finding the right file became a pain.
Alternative solution: treat your downloads folder as ephemeral and delete everything every few weeks.
I feel like we’re entering an age where there is going to be increasingly more data in every day lives. (Just think about every chat in your ChatGPT account)
I guess one solution is to make everything searchable and try to organize everything. Or start treating things as ephemeral.
There’s probably no right answer. E.g. the difference between people who like having 50+ tabs open in Chrome, and needing features to organize and search tabs, versus people who treat tabs as ephemeral and short lived. I’m in the latter camp, but maybe just a matter of personal preference.
Has anyone coined the term “digital hoarding” yet? :)
I'd recommend adding a video or gif that demonstrates how it works for organizing files. I kinda get it but would prefer to see it in action before downloading
Presale pricing is weird, or at least unclear. I am totally fine with pricing strategies where you buy a perpetual license for the current major version only but this seems like less than that. It appears that for $10 we can have something available for free that may be updated some unknown amount, but probably without any significant new behavior, and then we’ll get a discount that could very well be less than the $10 we put in.
You could improve the situation by presenting some kind of roadmap and indicating the limit of presale or stating clearly the amount, or a minimum amount, of discount on V1 offered to presale purchasers.
I haven’t yet tried the thing but it looks interesting. It also looks reminiscent of quickly implemented Whisper or GPT-3 front ends released a couple years ago. I’d like to better understand the value you’re providing over Apple Intelligence provided APIs.
Thanks a lot for the thoughtful feedback — I’ll definitely add a roadmap and make the presale terms clearer (e.g. version limits and minimum discounts). That’s very fair.
Regarding Apple Intelligence: you’re right, Apple is integrating more AI features at the OS level, but from what I’ve seen, it’s still quite limited. For example, semantic search are not really handled in a way that solves the problem. Fallinorg is built to work fully offline, across any file type, and with deeper control/flexibility than what Apple currently exposes through their APIs.
Put simply: if Apple ever does this well, great — but right now, I think there’s still a lot of room for a tool that is private, offline, and purpose-built for file management.
I could really really use something that would OCR and classify all the screenshots I take of stuff to remember. Have an enormous folder of the damn things.
> Email us at fallinorg@proton.me with ith your refund request and reason. We’ll be happy to assist you.
Not to be a jerk, but if copy-editing for a pre-sale AI feature that operates on my local files includes such an oversight, it doesn’t inspire confidence. I know copy-editing and coding are different domains, but I’m still put off by it.
Finances and Contracts are for me the same folders.
Also, spaces in folders will absolutely break my legacy scripts on `~` at a future time when I re-run them.
Demo is not that convincing. Also, I need multilanguage support, and am not clear if OCR for PDFs before running is done by this. (Which again, needs beforehand knowledge of which language the document might be in?)
But, cheap, and pay once and offline. Will keep an eye on it.
> Finances and Contracts are for me the same folders.
> Also, spaces in folders will absolutely break my legacy scripts on `~` at a future time when I re-run them.
Folder names and spaces: full customization is coming — you’ll be able to name and organize them however you like.
> Demo is not that convincing.
Demo: what felt missing or unconvincing? Any feedback helps improve it.
> Also, I need multilanguage support
Multi-language: on the roadmap — which languages matter most to you?
> and am not clear if OCR for PDFs before running is done by this.
currently not automatic for scanned PDFs. I’m also validating whether sorting images, videos, and audio based on their content/meaning would provide real value. What do you think?
Thank you so much for testing it and giving all this feedback!
If there were a CLI version, what would your ideal workflow look like? For example, would you want it to run as a one-off command on a folder, or as something you can integrate into cron/jobs/pipelines/...?
This is the kind of things Apple should focus on. Automatic file organization is right up Apple's alley, if they were ever to wake up the Finder's dev team from the 20-year hibernation.
I would guess that using an efficient embedding model to organize files is probably forthcoming in the next year or two.
Rather than moving similar files into folders, I can see the OS suggesting related files based on similarity to another file, or permitting search by concept rather than keyword.
I have has a couple of macs that randomly do not show "Recent" files in the recent folder so I take that as one signal among many that Apple is not paying a lot of attention to the experience in desktop environments beyond some minimal maintenance effort
I wanted to validate whether there’s real market interest and if people would actually be willing to pay for a tool like this, since it solves a real problem.
User can give example documents... have sbert test against dewey decimal classifications, or library of congress, also categories for home users (bills, manuals, bank documents, etc) and standard business categories (HR, production and so on). User verifies categories.
Onboarding would ask user about their work, research, hobby interests. LLM could generate word lists asking user if it matches their understanding. And so on.
It seems to be less of a "file organizer" than it is a "document organizer" since it only supports plain text and PDF files.
Personally, I don't think I have that many PDF and text files that organizing them manually would be a pain. The organization logic also is a miss for me, since I don't really organize my documents in buckets like "Legal & Contracts", but rather I have folders like "Car" (for my car's service records, bill of sale, owner's manual, etc.) and "Mortgage" (mortgage quotes, contracts, etc) that's housed under "Apartment".
Doesn't help that most of these documents are not in English.
You’re right — at the moment it’s limited to text and PDFs, but this is just the starting point. Support for more file types, more languages, and full customization (so you can define your own categories, folder names, and destinations) will be rolled out next.
I’d love to learn from your use case: what are the top 5 file types you find yourself storing most often on your Mac?
The Python 3.13 virtualenv you're bundling with the app is 357MB, while the ONNX model is only 90.4MB.
onnxruntime has Swift bindings[1], consider using that. Or better yet use CoreML. You'll also be able to support x86 Macs with either of those.
[1]: https://github.com/microsoft/onnxruntime-swift-package-manag...
Even without changing one byte of the actual binary they could get pretty far by just evicting all the test files for those packages they're including. And, related to that, it seems that dist-info/RECORD ends up at 1,050,544 because the onnx folks decided it was important that they cryptographically sign all those test data files they're choosing to ship :-/
Hi HN, Fallinorg is a local macOS app that organizes files by their meaning, not just their name or type.
Problem: My Downloads and Desktop folders kept filling up with cryptically named, duplicate, or unrelated files. Over time, cleaning up and finding the right file became a pain.
Solution: It uses Sentence Transformers (SBERT) to understand the content and context of files, then automatically groups them. It runs fully offline, so you can safely classify sensitive files (finance, medical, personal, etc.). On Apple Silicon, it parses, tokenizes, and categorizes a file in about ~1.2 seconds.
You can download and test it now for free: https://github.com/taranntell/fallinorg/releases/tag/1.0.0-b...
Current version: Supports .txt and .pdf files in English; I’m working on adding more formats and languages.
Looking for feedback on: Classification accuracy, speed, pricing ideas, and potential bulk operations or integrations.
I first launched a few weeks ago and have been rapidly adding features based on early feedback. Happy to answer questions and share implementation details.
Given that this is a Mac app, have you considered taking advantage of the considerable amount of metadata for files (sometimes including full text content) made available by QuickLook? It could extend functionality for many file formats without requiring the app to be able to parse them.
That's brilliant thank you I will investigate on this! I haven't thought about it.
> Over time, cleaning up and finding the right file became a pain.
Alternative solution: treat your downloads folder as ephemeral and delete everything every few weeks.
I feel like we’re entering an age where there is going to be increasingly more data in every day lives. (Just think about every chat in your ChatGPT account)
I guess one solution is to make everything searchable and try to organize everything. Or start treating things as ephemeral.
There’s probably no right answer. E.g. the difference between people who like having 50+ tabs open in Chrome, and needing features to organize and search tabs, versus people who treat tabs as ephemeral and short lived. I’m in the latter camp, but maybe just a matter of personal preference.
Has anyone coined the term “digital hoarding” yet? :)
> Alternative solution: treat your downloads folder as ephemeral and delete everything every few weeks.
Hazel[0] works well for this, but automatic download folder cleanup feels a lot like it should be a stock Finder feature.
[0]: https://www.noodlesoft.com
Moving files from Downloads to a specified archive folder every x days is also a “side“ feature of https://sindresorhus.com/supercharge
I'd recommend adding a video or gif that demonstrates how it works for organizing files. I kinda get it but would prefer to see it in action before downloading
The video will be displayed at the top of the homepage. Since I’m hosting it on GitHub Pages, the server might occasionally be overloaded.
You can also access the video directly here: https://fallinorg.com/assets/demo.mp4
This becomes interesting once you support epub, cbz, cbr.
Presale pricing is weird, or at least unclear. I am totally fine with pricing strategies where you buy a perpetual license for the current major version only but this seems like less than that. It appears that for $10 we can have something available for free that may be updated some unknown amount, but probably without any significant new behavior, and then we’ll get a discount that could very well be less than the $10 we put in.
You could improve the situation by presenting some kind of roadmap and indicating the limit of presale or stating clearly the amount, or a minimum amount, of discount on V1 offered to presale purchasers.
I haven’t yet tried the thing but it looks interesting. It also looks reminiscent of quickly implemented Whisper or GPT-3 front ends released a couple years ago. I’d like to better understand the value you’re providing over Apple Intelligence provided APIs.
Thanks a lot for the thoughtful feedback — I’ll definitely add a roadmap and make the presale terms clearer (e.g. version limits and minimum discounts). That’s very fair.
Regarding Apple Intelligence: you’re right, Apple is integrating more AI features at the OS level, but from what I’ve seen, it’s still quite limited. For example, semantic search are not really handled in a way that solves the problem. Fallinorg is built to work fully offline, across any file type, and with deeper control/flexibility than what Apple currently exposes through their APIs.
Put simply: if Apple ever does this well, great — but right now, I think there’s still a lot of room for a tool that is private, offline, and purpose-built for file management.
I could really really use something that would OCR and classify all the screenshots I take of stuff to remember. Have an enormous folder of the damn things.
…Or scans that come off a page scanner. For years, I’ve done it deterministically by looking for key data in the OCR; but the process is fragile.
Typo / editing issue:
> Email us at fallinorg@proton.me with ith your refund request and reason. We’ll be happy to assist you.
Not to be a jerk, but if copy-editing for a pre-sale AI feature that operates on my local files includes such an oversight, it doesn’t inspire confidence. I know copy-editing and coding are different domains, but I’m still put off by it.
Finances and Contracts are for me the same folders.
Also, spaces in folders will absolutely break my legacy scripts on `~` at a future time when I re-run them.
Demo is not that convincing. Also, I need multilanguage support, and am not clear if OCR for PDFs before running is done by this. (Which again, needs beforehand knowledge of which language the document might be in?)
But, cheap, and pay once and offline. Will keep an eye on it.
> Finances and Contracts are for me the same folders.
> Also, spaces in folders will absolutely break my legacy scripts on `~` at a future time when I re-run them.
Folder names and spaces: full customization is coming — you’ll be able to name and organize them however you like.
> Demo is not that convincing.
Demo: what felt missing or unconvincing? Any feedback helps improve it.
> Also, I need multilanguage support
Multi-language: on the roadmap — which languages matter most to you?
> and am not clear if OCR for PDFs before running is done by this.
currently not automatic for scanned PDFs. I’m also validating whether sorting images, videos, and audio based on their content/meaning would provide real value. What do you think?
Thank you so much for testing it and giving all this feedback!
Have you considered offering a Command-Line version as well? I would use something like this if it wasn't just an app and worked on Linux.
Would be neat if it studied your existing organizational patterns and tried to fit any changes to match it.
If there were a CLI version, what would your ideal workflow look like? For example, would you want it to run as a one-off command on a folder, or as something you can integrate into cron/jobs/pipelines/...?
This is the kind of things Apple should focus on. Automatic file organization is right up Apple's alley, if they were ever to wake up the Finder's dev team from the 20-year hibernation.
I would guess that using an efficient embedding model to organize files is probably forthcoming in the next year or two.
Rather than moving similar files into folders, I can see the OS suggesting related files based on similarity to another file, or permitting search by concept rather than keyword.
I have has a couple of macs that randomly do not show "Recent" files in the recent folder so I take that as one signal among many that Apple is not paying a lot of attention to the experience in desktop environments beyond some minimal maintenance effort
"Download Pre-Sale" is a bit sketchy. Why not just make a trial?
I wanted to validate whether there’s real market interest and if people would actually be willing to pay for a tool like this, since it solves a real problem.
That said, I’d love if you give it a try, here's the download link: https://github.com/taranntell/fallinorg/releases/tag/1.0.0-b...
There's definitely a real market. I'd recommend adding office documents next. And then user defined categories.
Thanks oidar, out of the big three (word, excel, PowerPoint) do you use another ms office documents?
Can you please elaborate more on how would you set up a user define category?
User can give example documents... have sbert test against dewey decimal classifications, or library of congress, also categories for home users (bills, manuals, bank documents, etc) and standard business categories (HR, production and so on). User verifies categories.
Onboarding would ask user about their work, research, hobby interests. LLM could generate word lists asking user if it matches their understanding. And so on.
Also open document format (CSV, TSV too).
It (at least the version on github) crashes on my macbook m1 pro
It seems to be less of a "file organizer" than it is a "document organizer" since it only supports plain text and PDF files.
Personally, I don't think I have that many PDF and text files that organizing them manually would be a pain. The organization logic also is a miss for me, since I don't really organize my documents in buckets like "Legal & Contracts", but rather I have folders like "Car" (for my car's service records, bill of sale, owner's manual, etc.) and "Mortgage" (mortgage quotes, contracts, etc) that's housed under "Apartment".
Doesn't help that most of these documents are not in English.
You’re right — at the moment it’s limited to text and PDFs, but this is just the starting point. Support for more file types, more languages, and full customization (so you can define your own categories, folder names, and destinations) will be rolled out next.
I’d love to learn from your use case: what are the top 5 file types you find yourself storing most often on your Mac?
Thanks for the feedback!