kshetrajna12/reflex

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

Jeeves – Reasoning improves Jev-like decision models

Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.

The open, local take on Jev: typed decisions from an LLM, without generating a single token

Typed decisions from a frozen language model and a small physics engine: calibrated probabilities, conformal sets, 73k context, images.

Open, Jev-compatible System One decision server on DiffusionGemma

Fast multi-modal decision model