All decision model projects

vLLM Semantic Router's Apache-2.0 decision models (0.6B to 27B) answering up to 64 typed questions per input in one forward pass.

OpenAI's Decisions API: GPT-6 Luna answers Noul, Choice and Score questions about text, JSON or images with a probability per option.

Superagent's Apache-2.0 security decision model from AutoJev-27B, scoring options for injection, tool calls, code and alerts.

Upstage's beta decision model on Solar Mini 4 with a 512K context and Jev's request format, offered on OpenRouter.

Software development framework for coding agents that hands dependency vetting, completion gates and debugging decisions to Jev.

Hosted decision model state-decider-1 answering Noul, Choice and Score via /v1/systemone, compatible with the TypeSafe SDK.

Inception's decision model on OpenRouter, with a free route, cited by Inception at up to 14 decisions per second.

Small personal model trained in the spirit of Jev; few public details beyond a one-line description.

SGLang's native /v1/decisions and /v1/systemone endpoints that read option probabilities from a validated chat model's next-token scores.

Respan's behaviour classifier for AI traces that returns present, absent or not observable for each plain-language behaviour you define.

Audio-native decision model for live voice agents that picks respond, wait, yield, backchannel or escalate straight from call audio.

Microsoft's hosted decision model announcement, claiming top accuracy on 36 benchmarks and low latency versus GPT-6 Sol.

Retrospective test of Jev 1.13 classifying 8,054 Kepler Objects of Interest against hidden NASA Exoplanet Archive dispositions.

Blog benchmark testing Jev against Mistral Small and Gemini Flash-Lite at validating local event listings, with cost and latency.

Independent leaderboard grading Jev and six LLMs on the same typed questions against human labels, with open per-decision data.

Static benchmark dashboard comparing Jev with two OpenAI Luna settings on Japan's 2026 university Common Test.

LangWatch comparison of Jev against seven open models under 1B on 15 decision tasks, with intervals, latency and contamination checks.

Working paper placing a text judge beside a live trading system as a read-only signal, comparing Jev and Claude as blind headline judges.

Paper testing, without labels, whether Jev's probabilities obey probability axioms such as P(X) + P(not X) = 1.

Paper on where Jev and Laya fit in LLM pentest agents: finding adjudication, severity recalibration, pruning and confirmation loops.

Paper introducing an encoder-only System One model for Chinese with domain fine-tunes and the CJ-Bench benchmark.

Paper evaluating zero-shot Jev 1.13 on 37 datasets against Qwen and Gemma option probabilities, with code and raw responses released.

Paper testing Jev, Laya, Decider and Nimble against classifiers and LLM judges on prompt injection and risk screening.

Paper introducing PixelJev, a native-image decision interface on small open multimodal models with few-shot adaptation.

arXiv paper surveying 2,170 public Jev GitHub projects to map ecosystem growth, application domains and decision-use patterns.

Paper introducing an adversarial benchmark for decision models: one appended opinion flips 12.1% of Jev 1.13 decisions.

Paper auditing 28 early Jev papers and proposing a 14-item checklist for evaluating typed decision models.

Independent paper testing Jev's self-reported fields against ground truth, finding a collapsed verdict vocabulary and misleading flags.

Unaffiliated directory of Jev plugins and tools ranked by stars, with a tutorial and a Laya vs Jev vs Kev comparison.

Official TypeSafe cookbook showing how to judge retrieved passages with Jev before passing them to an answering model.