Newborn 
PY Training-free decision engine for existing MLX models on Apple Silicon. No fine-tuning or extra decision weights. MLX-LM + experimental MLX-VLM action selection and semantic routing. Related: AnyJev.
HEALTH ? 77 / Stable
Newborn PY // readme
MLX Direct Decider — MLX decision engine without fine-tuning
MLX Direct Decider is an open-source Python library for training-free decisions from existing MLX models on Apple Silicon Macs. Use it for local LLM action selection, classification, semantic routing, and enum / boolean decisions.
Reuse a compatible MLX-LM checkpoint for text or an MLX-VLM checkpoint for experimental text + image decisions. Supply application state, a natural-language request and allowed choices; receive a stable candidate ID, no_match or abstain. Integrate through a Python API, CLI or local text HTTP service.
No additional fine-tuning, trained decision head or separate decision-model weights are required. The full model processes the prompt normally; the library reads candidate logits from its unchanged original output head without generating a continuation. Compatible base-model weights are still needed.
JevBench public evaluation: 74.0% — 171/231 correct, without additional fine-tuning. Qwen3.5-9B OptiQ mixed 4/8-bit · Apple M2 Max · evaluated Q&A prompt profile. Self-reported results on…