🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
A source-reviewed gallery of JEV-related projects with 50+ GitHub stars — integrations, tools, open models, experiments, and ecosystem resources. Live gallery: beatapi.io/awesome-jev
Provider-neutral System One runtime for TypeScript and Pi
Research design for a Jev-native agent system: tool integration, speculative parameter proposals, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.Feature:Jev naturallanguage conversation prototype using external helper logits and dynamic Top-k token selection.
Independent, reproducible benchmark: a decision model (jev), eight constrained LLMs, and deterministic baselines on typed decisions - accuracy, calibration, latency, cost, failure modes
ReflexBench — open benchmark and evaluation harness for System One models and typed decision engines
Open schemas, recipes, templates, examples and agent tooling for Brida Reflex.
Train lightweight language backbones for typed decisions and candidate probabilities. CE/Brier training, evaluation, and an offline end-to-end demo.
Black-box reverse engineering research archive for the Jev decision model
Daily curated Jev AI projects, System One community models, and real-world use cases.
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.
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.
Your hardware. Local decision models. Turn messy state into typed choices, scores, and yes-no calls over TypeSafe-compatible HTTP and MCP. No cloud bill.
Curated catalog of System One / Decision Models — contributions for modelsystem.one
Train and inspect a small decision model on your Mac. Public data, full fine-tuning, honest evaluation, and downloadable weights.
Self-hosted, Jev-compatible decision-model API — one /v1/systemone endpoint, open weights (Laya, kev), one Docker image per engine.
Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.
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.
Code for JevOut: Natural Context Can Flip Decision Models
To associate your repository with the decision-models topic, visit your repo's landing page and select "manage topics."