A Pi extension that calls TypeSafe's Jev model after an agent run settles, and sends a continuation prompt only when Jev detects unfinished work above a configured threshold. Includes configurable settings, evidence validation, and tests.
该仓库实现了一个 Pi 扩展，在 agent 运行结束后调用 TypeSafe Jev 模型评估未完成工作，并根据阈值决定是否发送继续提示。README 包含安装、配置、数据发送说明和测试，属于真实使用 Jev 的集成项目。
TypeSafeAITypeSafeAI/jev-harnessOfficialTypeSafeAI community repository implementing a Jev-based proposal-review workflow: an LLM proposes, Jev answers four narrow questions, code decides and leaves receipts; includes offline tests, routing experiments and a Next.js demo.
ekzhangekzhang/openjev-sglangJev-compatible API endpoint based on open models (prefill-only), implementing TypeSafe Jev/System One evaluation endpoints with Qwen3.6-35B-A3B on SGLang.
keltokhykeltokhy/jgrepjgrep is a CLI semantic grep that calls TypeSafe's Jev/System One decision model to judge lines or diff hunks by description, returning probabilities instead of generated text.
