uzu vs xybrid
Rust inference engine for on-device AI on Apple Silicon (Metal, unified memory) with Swift, Python and TS bindings, OpenAI-compatible server and a TypeSafe System One decision-model API. — 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.
Both are embeddable on-device inference SDKs with Swift and Rust bindings for shipping private, offline LLMs in apps; xybrid spans more platforms on llama.cpp/ONNX, uzu goes deep on Apple unified memory.
| uzu | xybrid | |
|---|---|---|
| Stars | 3.2k | 513 |
| Forks | 221 | 58 |
| Language | Rust | Rust |
| License | MIT | Apache-2.0 |
| Last activity | yesterday | yesterday |
| Topics | local, decision-models | local, voice |
| Curated connections | 5 | 5 |
uzu — the curator's take
Pick it when you are shipping an iOS/macOS app and want a local LLM embedded in-process — Swift Package, structured output, tool calls, and a cloud fallback through the same API. Not for NVIDIA/Linux serving (Metal and CPU only) or bring-your-own GGUF: models need its own format, converted with lalamo.
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.