strands-decider vs uzu
Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU. — versus — 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.
Both serve a small decision model locally behind the TypeSafe-style /v1/systemone API with typed choice, yes/no and score answers; Strands runs on CUDA/MPS/MLX/CPU, uzu on its Metal engine.
| strands-decider | uzu | |
|---|---|---|
| Stars | 763 | 3.2k |
| Forks | 108 | 221 |
| Language | Python | Rust |
| License | Apache-2.0 | MIT |
| Last activity | 2 days ago | yesterday |
| Topics | decision-models, local | local, decision-models |
| Curated connections | 6 | 5 |
strands-decider — the curator's take
Use it for the many small judgments inside an agent workflow — routing, triage, urgency, sentiment — where an LLM call is too slow and training a classifier too much work; answers at ≥0.9 confidence were right ~95% of the time on unseen tasks, so threshold and escalate the rest. It decides, never writes. At 2B it runs on a laptop; for agent-action ranking at scale, CLM's cached-embedding design is faster.
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.