Browser simulation using TypeSafe AI's Jev for parallel team decisions, with capacity-constrained assignment and retained benchmark evidence.
仓库使用 TypeSafe AI 的 Jev 模型进行并行团队决策模拟，包含 API 调用、SDK 传输测试、可运行 demo 和保留基准证据，实质内容充分。
zjunlpzjunlp/JevLoopJevLoop is a zero-dependency TypeScript agent loop that routes control decisions to TypeSafe AI's Jev decision model, reserving LLM calls for generation. It includes a runnable demo, DECISION.md policy compilation, and benchmark/latency comparisons.
buberlobuberlo/dsh-jevA DeepSeek Harness plugin that uses TypeSafe Jev/System One for dynamic tool selection, pre-execution call assessment, model routing, and skill routing. Includes runnable examples, 120 tests, 25 evaluation fixtures, and a with/without-Jev benchmark.
sugarforeversugarforever/tryjevAn interactive playground for TypeSafe AI's Jev System One decision model. It offers preset scenarios, typed questions, and probability-based answers via OpenRouter, Vercel AI Gateway, and TypeSafe API.
