jelight is a library that uses TypeSafe AI's Jev model to classify code tokens by semantic role, providing fast base highlighting and optional Jev-powered refinement. It supports Vercel AI Gateway and direct TypeSafe API providers.
仓库 README 明确说明使用 TypeSafe AI 的 Jev 模型进行语义代码高亮，包含直接调用 TypeSafe API 的适配器和 Vercel AI Gateway 适配器，并提供了可运行的示例，真实集成并使用了 Jev。
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.
