Ross ROSS = Recommend OSS · open-source software intelligence for agents

mazzzystar/Queryable

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos. observed · 2026-08-28

github.com/mazzzystar/Queryable · homepage · Swift · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

62/100

  • Activity 74
  • Release rhythm 35
  • Longevity 82

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 1152
  • days_rel: n/a
  • days_push: 157
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2977 stars · 452 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

application · maturity active

search-engine machine-learning image-processing nlp machine-learning image-processing privacy mobile-development clip mobileclip semantic-search photo-search offline swiftui natural-language-image-search on-device-ai ios macos swift

2 sources

Member repositories

RepositoryRoleHealth v2
mazzzystar/Queryablemain62

For agents

markdown · JSON · MCP: product_card(name="mazzzystar/Queryable")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem