Clean up the photos that were never meant to be memories.
Your camera roll has a junk drawer: the receipt for an expense report, the parking-garage pillar, the Wi-Fi password on a whiteboard, the serial number on the back of the router, the shelf you photographed to remember what to buy. Ayos finds them, tells you why it thinks each one is temporary, and lets you clear them out in one pass. Everything happens on your device.
Ayos: Photo Cleaner
Not every photo is a memory. Ayos sorts the ones that aren't into a pile called Possible Not a Memory, alongside duplicates, similar shots, screenshots, blurry photos, and large videos. You review, you decide, your photos app does the deleting.
What it finds
- Possible Not a MemoryReceipts and documents, products and shopping, food, memes and saved images, utility and reference shots, old screenshots.
- DuplicatesExact copies. The best one is kept.
- Similar photosNear-identical shots of the same moment, with the best one picked.
- ScreenshotsScreenshots and screen recordings from the last two years.
- BlurryToo little detail to be a usable photo.
- Large videosVideos over 100 MB, biggest first.
Every photo carries its reason: This looks like a receipt from March 2023. Still need it? High-confidence items come pre-checked, everything else is one tap away, and the uncertain ones can be reviewed one at a time.
What it never does
- Upload anything. Analysis runs on the device: Apple's on-device frameworks on iPhone and Mac, Google's on-device ML Kit on Android. There is no account, no cloud, no analytics, and the app makes no network connections of its own.
- Delete on its own. You choose what goes into the Review bin. Deleting schedules them: they wait in Ayos for 7 days, where a tap takes any back, and only then go to your photos app, which asks you once more and keeps them 30 days in its trash (Recently Deleted on iPhone and Mac). Impatient? Delete now is always there.
- Suggest your favorites. Favorites never appear. Photos of people, pets, and trips are ranked last for any suggestion, and every suggestion comes with a reason you can read.
Why we built it
Most of our work is about protecting the data people keep. Ayos is the other half of that: deciding what not to keep, with the decision explained and left to the person. It is also a working test of how far on-device image analysis can go without sending a single photo anywhere, on Apple's frameworks and on Android's, and we will write up what we learned once it has been in real hands. The launch note is on Insights: Ayos: Photo Cleaner is now available on iOS and Android.
Support
Questions, a photo that was flagged and shouldn't have been, or a purchase that didn't unlock: hello@horizondigital.dev. Include your device and its OS version and what you were doing; you will get a reply from the person who wrote the app.
Privacy policy for the app: Ayos privacy policy.