Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Community model zoo for Apple Core AI (iOS/macOS 27): 57 models — LLM, VLM, OCR, ASR, TTS, image/video/music gen, forecasting — each gated against its source model and shipped with the recipe that produced it. Downloadable from Hugging Face, runnable in one line of Swift via CoreAIKit. Plus benchmarks, Metal kernels, knowledge base.
| Date | Stars |
|---|---|
| 2026-07-31 | 374 |
| 2026-08-06 | 380 |
Today
+6 stars today
This week
— stars this week
This month
— stars this month
Momentum
39.0
growth rate 0.00%/day
# CoreAI-Model-Zoo [](https://github.com/john-rocky/coreai-kit/releases) [](https://huggingface.co/mlboydaisuke) [](https://github.com/john-rocky/coreai-kit/actions/workflows/ci.yml) [](https://github.com/john-rocky/coreai-kit/actions/workflows/nightly-gate.yml) **Converted models + conversion recipes** for Apple **Core AI** (`.aimodel`, iOS 27 / macOS 27): every model here is downloadable, gated against the original model before it ships, and carries the recipe that produced it in [`models/<model>/recipe.toml`](models/) — rerun it (`zoo_convert.py run <name>`), check the published bundle against its source model (`zoo_verify.py`), or adapt it for your own port. **Don't take the gates on faith — they are run here, and everything needed to re-run them is published.** Each card states what was measured on which hardware (iPhone tier is device-measured; the large models are Mac-only and say so) and how strong that model's parity proof is, because it differs per model. Where the shipped configuration could not be recovered from the repository, the recipe says so rather than guessing. Model ports are open to everyone — the catalog serves community ports from the contributor's own Hugging Face namespace (first: [Nanbeige4.2-3B](models/nanbeige4.2-3b/README.md) by [@ukint-vs](https://github.com/ukint-vs)). Successor to [`CoreML-Models`](https://github.com/john-rocky/CoreML-Models). **The `from_pretrained` of Core AI** — one line, any zoo model, via [**CoreAIKit**](https://github.com/john-rocky/coreai-kit) (SPM): ```swift let chat = try await ChatSession(catalog: "qwen3.5-2b") // downloads once, then cached let reply = try await chat.respond(to: "What can you do, offline?") ``` Same gesture for every capability — `KitTranscriber(catalog: "whisper-large-v3-turbo")` is speech-to-text in 3 lines ([card](models/whisper-large-v3-turbo/README.md)). Each model's card carries the complete copy-paste snippet and its integration checklist. Every row below also links a ready-to-build app — in this repo's [`apps/`](apps) or a [CoreAIKit example](https://github.com/john-rocky/coreai-kit/tree/main/Examples) (marked ↗). Chat models also plug straight into **Apple's FoundationModels API**: `LanguageModelSession(model: try await KitLanguageModel(model: .qwen3_0_6B))` gives you the system session — `Tool` calling, `@Generable` guided generation, transcripts — backed by a zoo model ([how](https://github.com/john-rocky/coreai-kit#works-with-apples-foundationmodels-api)). Zero-dependency alternative: every bundle loads with Apple's own `CoreAILanguageModel(resourcesAt:)` as-is; this repo's [`ZooFMProvider`](swift/Sources/ZooFMProvider) adds streaming tool calling on top (incl. LFM's native dialect) — engineering notes in [`knowledge/fm-provider.md`](knowledge/fm-provider.md). ## Quickstart — running a model on your device New here? You'll have a model answering on-device in a few minutes (needs Xcode 27 + a Mac or an iPhone/iPad on iOS/macOS 27): ```bash git clone https://github.com/john-rocky/coreai-kit open coreai-kit/Examples/ChatDemo/ChatDemo.xcodeproj # Run, then pick a model in the picker ``` The app downloads the model on first pick (cached after), then runs it fully offline. **Start small for the fastest first run:** `Qwen3-0.6B` (454 MB) or `Qwen3.5-2B` on iPhone; any of the Mac-only rows on a Mac. Prefer the terminal? `swift run chat-cli --model qwen3-0.6b --prompt "Hello"` from `Examples/ChatDemo`. To drop a model into **your own** app, copy the snippet from that model's card — it's the same `catalog:` on
Excerpt of 40,974 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:45a5851958cf6b86, topic:llm, topic:qwen