decision-models

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

A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.

🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.

JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.

A source-backed Jev / System One knowledge map: projects, papers, evaluations, robotics, and social discovery.

Bud Decision studio is an easy to use cross platform desktop application & serving system for Jev like models locally.

Provider-neutral System One runtime for TypeScript and Pi

Evals that meet you where you are. For AI that's grounded.

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

The most complete gallery of what people build with Jev, TypeSafe's System One model: 3,400+ projects, demos, and write-ups by scenario, each with its original link, image, and description.

EmbeddingGemma2 resources: local search apps, decision models, inference frameworks, tutorials, and datasets. English / 简体中文.

Benchmark Heaven: AI model benchmarks with sources and modeled costs, plus the JevBench and ImageJevBench decision model leaderboards.

Independent, reproducible benchmark: a decision model (jev), eight constrained LLMs, and deterministic baselines on typed decisions - accuracy, calibration, latency, cost, failure modes

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.

A high-performance serving engine for System One decision models.

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

What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.

Run fast, typed AI decision models behind one API. Choice, score and yes/no decisions with multiple engines and hardware backends.

ReflexBench — open benchmark and evaluation harness for System One models and typed decision engines

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