AI photo search, in your own words
Somewhere on your Mac is a photo of a red umbrella in the rain, and you know it exists. Filenames like IMG_4832.HEIC give you nothing to search for, so you scroll thumbnails folder by folder. PhotoCore reads the content of every image on device and finds that photo from a plain description, in under 50ms across 10,000 photos.
Why filename search fails
Finder and Spotlight match file names and a little metadata. A photo you never renamed carries no words to match, so the umbrella, the rainy street and the person under it are invisible to them. You end up scanning thumbnails by eye, and a two-minute task turns into twenty. PhotoCore takes another route: it looks at the pixels, so what you type is matched against what each image actually shows.
Describe the photo, get the photo
A model that reads images, on your Mac
PhotoCore runs SigLIP 2 through Core ML on the Apple Neural Engine. During indexing, each photo becomes a 768-dimension embedding stored in a local SQLite database. When you search, your words become an embedding too, and cosine similarity via Accelerate.vDSP ranks every image against them. The result: a search across 10,000 photos answers in under 50ms, in the language you think in.
- Type 'red umbrella in the rain' and press return
- Results in under 50ms across 10,000 photos
- Search in more than 100 languages
Search with an image instead of words
Sometimes the best query is another photo. Pick any image in your library and PhotoCore finds the shots that look like it. You can also drag and drop a reference image that was never indexed, straight from an email or a website, and search your archive against it. A tolerance slider decides how close a match must be, from near-duplicates to loosely related scenes, in visual or hybrid mode.
Narrow the results until one screen holds the answer
Person @mentions
Add a person to any query, like '@Anna at the beach'. Name someone once and mention them anywhere.
People count
Filter by how many people are in the frame: 0 for clean landscapes, exactly 2 for couples, more than 5 for groups.
Quality
Sort results by an on-device quality score so the keepers rise to the top of any view.
Map
See matches as pins on Apple Maps, grouped by place, and click a pin to open the photo.
Date range
Limit any view to exact days with the calendar filter, like the last two weeks of May.
Private by design
Every step runs on your Mac. There is no cloud, no account and no tracker, and search keeps working offline. Folders are indexed in place and read-only, including folders on external drives and NAS shares, which stay searchable after you disconnect them. Curious about the internals? Read how semantic photo search works, or see the everyday version on find photos by description. AI Find is one of seven tools on the features page.
Related pages
How semantic search works
Embeddings, cosine similarity and the Neural Engine, explained in plain language.
Find photos by description
Real search phrases and what they bring back, from archives spread across drives.
Face recognition
Name a person once and find every photo of them, with @mentions in any search.
All features
Search, people, quality, maps, Constellation, Semantic Bridge and rename in one app.
Frequently asked questions
Does AI photo search work offline?
What can I type in the search box?
How fast is search on a big library?
Which image formats does PhotoCore index?
Type it. Find it.
Download PhotoCore free and index up to 200 images to try search by meaning on your own archive. Full access is a one-time purchase of 59.99 euro, or 29.99 euro Early Bird until July 15.