An experimental source-aware memory admission evaluator powered by Jev. It calls the TypeSafe Jev API to classify candidate memories as save, skip, or defer, and includes editable cases, a local CLI/JS entry point, and published evaluation reports.
仓库 README 明确展示了直接调用 TypeSafe Jev API 的 CLI、JavaScript 入口、本地 demo、多组冻结评测协议与报告，并记录 jev-latest/jev-1.13.0 结果，属于真实集成与深入研究。
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.
