🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
We only curate source-reviewed JEV-related projects with 100+ GitHub stars — integrations, tools, open models, and experiments. Live gallery: beatapi.io/awesome-jev
Independent, reproducible benchmark: a decision model (jev), eight constrained LLMs, and deterministic baselines on typed decisions - accuracy, calibration, latency, cost, failure modes
Train lightweight language backbones for typed decisions and candidate probabilities. CE/Brier training, evaluation, and an offline end-to-end demo.
Provider-agnostic TypeScript SDK for decision models — typed answers with calibrated uncertainty, instead of text you have to parse. Pre-release, not on npm yet.
Curated catalog of System One / Decision Models — contributions for modelsystem.one
Open models, libraries, tools, and applications for Jev and System One decisions.
Curated directory of real-world tools, interactive video teardowns, empirical benchmarks, and fast System One decision models.
Open schemas, recipes, templates, examples and agent tooling for Brida Reflex.
Train and inspect a small decision model on your Mac. Public data, full fine-tuning, honest evaluation, and downloadable weights.
Jev makes every flap-or-coast decision in a live game, exposing probabilities, latency, tokens, and cost.
A Jev practice catalog and local-first Agent skill router: map recurring logs to reusable decisions, tools, and workflows.
小模型只做选择，宿主掌握所有权：把「任务足够固定时，不要让模型写它能选的东西」量出来 | Selection-only: host enumerates candidates, a tiny model picks one id, host assembles deterministically. All numbers measured on one M1 Pro.
Finite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee breaks.
Independent playground for TypeSafe AI Jev decision models: typed decisions, support-ticket routing, reproducible evaluations, and a local browser demo.
Dynamic two-stage skill & tool pre-filtering for OpenClaw using Decision Models (Jev / TypeSafe)
Option-ready retrieval for decision models on the CloudBTL landing layer
To associate your repository with the decision-models topic, visit your repo's landing page and select "manage topics."