StackMap
Subscribe

coreai-models vs xybrid

Apple's official Core AI toolkit: recipes exporting Hugging Face models to .aimodel, PyTorch primitives for authoring, Swift runtime for macOS/iOS apps — plus skills for coding agents. — versus — Cross-platform on-device AI toolkit: run LLMs, ASR and TTS natively from Flutter, Unity, Kotlin, Swift or Rust on a llama.cpp and ONNX Runtime core. Private, offline, no cloud.

The curated verdict

Both put open models inside apps rather than behind an API. Apple's toolkit is deeper on one platform — .aimodel export and a Swift runtime tuned for Apple silicon; Xybrid trades that depth for reach across Flutter, Kotlin, Unity, Rust and the web.

coreai-modelsxybrid
Stars1.6k425
Forks15445
LanguageSwiftRust
LicenseBSD-3-ClauseApache-2.0
Last activity5 days agoyesterday
Topicslocallocal, voice
Curated connections33

coreai-models — the curator's take

The sanctioned path to shipping models inside Mac and iOS apps: export recipes take popular open models to Core AI format, the Swift package handles tokenizers and multi-model pipelines at runtime, and the bundled agent skills teach Claude Code/Codex the framework — Apple shipping skills for coding agents is itself a signal. NOT for experimentation velocity: this is the deploy-in-an-app stack, not the tinker stack (MLX is where Apple-silicon research lives), it requires macOS/iOS 27+ and Xcode 27+, and you're accepting Apple's format and release cadence as your foundation.

xybrid — the curator's take

The pick when the model has to ship inside the app — a mobile feature, a desktop tool, or AI NPCs in a Unity game — rather than behind your API. One Rust runtime, real SDKs per platform, and text plus speech in and out, so a voice assistant doesn't mean three vendors. The Unity binding with a playable 3D tavern demo is the differentiator; nothing else in the local stack targets game engines seriously. Check maturity per binding before committing: Flutter, Kotlin, Unity and the CLI are available, Swift is 'coming soon', and the browser SDK is a preview LiteRT.js adapter with raw typed-tensor I/O only. At 425 stars this is early, and on-device means you own model sizing, thermals and battery.