# mazzzystar/Queryable

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

Repository: https://github.com/mazzzystar/Queryable
Canonical: https://ross.abutalabs.com/products/queryable
Homepage: https://apps.apple.com/app/id1661598353
Language: Swift
License: MIT
License Family: permissive
Topics: ios, photos, search, swiftui, clip-model, semantic-search, mobile, natural-language-image-search, mobile-clip, mobileclip, macos, openai-clip
Last push: 2026-03-29T14:30:04+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 35, longevity 82
- inputs: {"age_days": 1152, "days_push": 157, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2977, forks 452 (observed 2026-08-28T04:07:32.998492+00:00)

## What it is
Queryable is an open-source iOS app that runs Apple's MobileCLIP (formerly OpenAI's CLIP) entirely on-device to search your photo album with natural language descriptions. All indexing and search happen offline, so photos never leave the device.

## Use cases
- find photos by natural language description on iphone
- search photo album offline with text like 'a brown dog on a bench'
- run CLIP model on iOS for semantic photo search
- private on-device photo search without uploading to cloud
- search photos in non-English languages on device
- build an image embedding index of an iOS photo library

## When to choose
- you want privacy-preserving, fully offline natural-language photo search on iPhone or Mac
- you want a reference implementation of running CLIP/MobileCLIP on-device with Core ML
- you prefer a one-time purchase app with open-source code

## When to avoid
- you need photo search on Android or web (see the companion PicQuery project for Android)
- you need server-side or cloud-scale image search across large datasets
- you need a reusable library or SDK rather than a standalone app

## Facets
- artifact type: application
- maturity: active
- function: search-engine, machine-learning, image-processing, nlp
- domain: machine-learning, image-processing, privacy, mobile-development
- platform: -
- tags: clip, mobileclip, semantic-search, photo-search, offline, swiftui, natural-language-image-search, on-device-ai, ios, macos, swift

## Member repositories
- mazzzystar/Queryable (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.998492+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:31:33.862494+00:00, confidence not recorded.
  - readme: https://github.com/mazzzystar/Queryable (fetched 2026-08-28T04:07:32.998492+00:00, sha 2ad29ff5fa19)
  - homepage: https://apps.apple.com/app/id1661598353 (fetched 2026-08-29T09:46:41.328979+00:00, sha 67ee444a000e)
- Data as of 2026-08-30T08:39:29.467469+00:00.