Uses TypeSafe's Jev evaluation model through eve and the AI Gateway to judge every file in a pull request against Clean Code, then Luna writes the review. Includes a live Next.js web app, CLI scripts, and an MCP server.
该仓库通过 eve 和 AI Gateway 真正调用 TypeSafe 的 Jev 评估模型，对 PR 中每个文件按 Clean Code 进行评判，并提供可运行的 Next.js 应用、CLI 与 MCP 服务器，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.
