Captures decisions, measures calibration, prioritizes human review by uncertainty, and exports fine-tune datasets for System One models like TypeSafe Jev/Laya. Includes a Jev adapter, but blocks training on Jev outputs per license.
仓库明确针对 TypeSafe 的 Jev 和 Laya 等 System One 模型，提供 Jev 适配器（JevProvider），并进行了实际测试（如 Laya 客户服务示例），且 topic 包含 jev。项目涉及 Jev 的集成与观察，符合收录标准。
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.
