Calibration & Research

AWS Strands Labs' 2B decision model: Qwen3.5-2B with a pointer head scoring options and calibrated confidence, plus a CLI.

Apache-2.0 open-weight Jev alternative that answers yes/no, choice and score questions with per-option probabilities in one pass.

Python library that gets typed, calibrated decisions from any open-weights LLM in one forward pass, with packed shared-state questions.

Drop-in local replacement for Jev that serves /v1/systemone from open weights, including questions about images.

Local decision engine on zero-shot ModernBERT and SigLIP2 answering Choice, Noul, Score and Relation over text, documents and images.

Local Jev alternative on zero-shot NLI models with temperature scaling and conformal abstention; reports ECE 0.170 to 0.071, offline.

Serving layer that runs typed-decision models like Laya on your GPU or Mac behind a Jev-compatible /v1/systemone API.

Library and MCP server that scores a fixed set of choices with a model you already run (llama.cpp, Ollama, OpenRouter).

Open family of System One-style models fine-tuned from Qwen3.5 and Gemma that return typed decision probabilities in one pass.

Open multilingual System 1 decision engine built on Laya checkpoints with a router that picks the best checkpoint per request.

Nace.AI's open Drex decision models (v2.0 MoE, v1.5 9B, diffusion DLM) serving /v1/systemone locally via Python, llama.cpp or Ollama.

Apache-2.0 local decision model (0.8B Qwen fine-tune on llama.cpp) behind the Jev request shape, calibrated and CPU-only.

Small open vision-language decision models (2B, 4B, 9B) that answer typed questions about photos and records with a trained can't-tell.

0.8B open System One model with task adapters that makes millisecond decisions in front of a larger local model like Qwen3.8-27B.

Local /v1/systemone server in Japanese docs with LFM, Sarashina and fine-tuned ModernBERT-Ja backends, including image input.

AutoTrust's Apache-2.0 student of Jev 1.13 on Qwen3.8-27B, serving typed decisions and ordinary generation from one vLLM engine.

AutoTrust's vision version of JEV-27B, ranked first of 20 on the community Jev Decision Index vision board.

Local Jev-compatible /v1/systemone server answering Noul, Choice and Score from open-weight models, usable with the official SDK.

Makes any logprob-capable model answer typed questions Jev-style in one pass, in Jev's API shape, with probes and scorecards.

Scores every allowed option of a typed schema from one MLX prefill on Apple Silicon and assembles schema-valid JSON with probabilities.

Small open decision models (0.8B and 4B, from Qwen3.5) with a server that speaks Jev's /v1/systemone format in one forward pass.

Toolkit that turns Laya into a task specialist: LLM-generated and verified training data, RLCD training, calibration and longer context.

From-scratch Rust reimplementation of Laya on candle, including the encoder, decision head, calibration, RLCD training and a server.

CLI and Claude Code skill that turns one typed decision into a fine-tuned, calibrated, evaluated Laya checkpoint you can serve.

Open System One decision model (LoRA on Qwen3.5-4B) that reads typed answers from logits in one pass, with its benchmark harness.

Zero-training toolkit that turns local LLMs and multimodal models into Jev-style decision services via prefill-only scoring.

Open recipe: describe a decision task, have an LLM write training data, and train a Qwen LoRA plus decision head with calibrated outputs.

HTTP server for Mica, a 4B open decision model with 32k context serving yes/no, choice and score in TypeSafe's /v1/systemone format.

TokenRhythm's NeoHorse repo: open 4B/9B agent models plus NeoHorse-Jev-4B, a prefill-only Choice/Noul/Score decision model.

Hugging Face card for NeoHorse-Jev-4B: Apache-2.0 4B decision model for text or image-plus-text, served at /v1/systemone.