A local agent harness that uses TypeSafe Jev/System One for typed judgments (classification, ratings, calibrated yes/no), letting an LLM only write prose; includes plan, route, assess workflows.
README 明确说明该仓库将 TypeSafe Jev / System One 放在普通 LLM 之前，由 Jev 负责类型化判断、路由、评估等任务，并包含计划、研究、应用生成等具体工作流实现，属于真实、深入的 Jev 集成项目。
walidboulanouarwalidboulanouar/jev-agent-kitCLI and MCP tools for agents using TypeSafe Jev to make fast typed decisions: route, triage, guard, grep, rank, compact, and judge. Includes runnable use-case demos and an offline evaluation script.
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.
