ReallyArtificialReallyArtificial/stuntdoublestuntdouble: Shadow proxy evaluation for Jev
A zero-dependency Node proxy that shadows TypeSafe Jev with local models (Kev, Laya) on live traffic and produces a report on whether you can swap.
106MIT
jev-writer: Writing analytics with TypeSafe Jev
Open-source content analytics and LLM-as-judge harness that rates posts with calibrated judgments from TypeSafe Jev (System One) and tests them against real engagement data.
仓库 README 明确说明使用 TypeSafe AI 的 Jev / System One 模型返回校准概率评分，并包含 TypeSafe 直接 API 支持、CLI、测试、Agent skill 及统计校验流程，并非空仓库或仅堆关键词。
· 1 starsOpen on GitHub
More like this
ReallyArtificialReallyArtificial/stuntdouble
NearCaiNearCai/JevLightJevLight: CityFlow-based Traffic Signal Control Evaluation Framework
A CityFlow-based traffic signal control framework that evaluates TypeSafe Jev and OpenAI-compatible LLM controllers alongside rule-based and reinforcement-learning baselines through the same simulation pipeline.
000MIT
killerz3killerz3/jevalyzerJevalyzer - Grade agent sessions with Jev
A CLI that reads local coding agent session logs and scores them using Jev, TypeSafe AI's System One model, producing interactive HTML reports and terminal dashboards.
200MIT