A TypeScript coding agent CLI that integrates TypeSafe AI's Jev (System One) as the decision model: Jev picks tools, scores progress and risk, while a configurable OpenAI-compatible LLM executes the work.
仓库为 TypeScript 编写的 coding-agent CLI，README 明确将 TypeSafe AI 的 Jev/System One 作为默认决策模型，并调用 api.typesafe.ai 与 jev-latest，包含配置、离线 mock 测试及 Laya 对比文档，属于真实集成。
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.
