9pings/notjev

Opensource Jev

Jev-compatible API endpoint based on open models (prefill-only)

Jeeves – Reasoning improves Jev-like decision models

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.

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

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.

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.