decision-models

🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

Provider-neutral System One runtime for TypeScript and Pi

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

Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.

Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.

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.

Self-hosted, Jev-compatible decision-model API — one /v1/systemone endpoint, open weights (Laya, kev), one Docker image per engine.

Black-box reverse engineering research archive for the Jev decision model

Train lightweight language backbones for typed decisions and candidate probabilities. CE/Brier training, evaluation, and an offline end-to-end demo.

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.

Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning; Jev and open-rlcd System One decisions get audit and calibration. Live dashboard, single Go binary.

Curated directory of real-world tools, interactive video teardowns, empirical benchmarks, and fast System One decision models.

Daily curated Jev AI projects, System One community models, and real-world use cases.

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.

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

Curated catalog of System One / Decision Models — contributions for modelsystem.one

Seems: Python, plus judgment, answered locally by Laya. A variant of kavehmz/seems-lang with the open-weight decision model swapped in for TypeSafe Jev.