This open-source tool translates SRT subtitles using OpenRouter LLMs and checks every source–translation pair with Jev. Jev flags subtitles that may need human review; the default QC model is typesafe/jev-1.13.
该仓库真实集成 TypeSafe Jev：默认使用 typesafe/jev-1.13 模型对每条字幕翻译执行质量检查，README 描述了 Jev 标记可疑翻译并交由人工复核的完整流程，源码包含 qc.py 与 openrouter.py 等实现，topics 含 jev 与 typesafe-ai，属于实质集成，而非空仓库或关键词堆砌。
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.
