AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證Reliability harness for AI agent actions: fault injection, read-back reconciliation, safe recovery, persisted traces, and evals.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Relay is a production-shaped reliability harness for agent actions against mutable business systems. It injects failures around a synthetic source-of-record adapter, reads state back after attempted mutations, reconciles intended versus observed effects, and decides whether to complete, retry safely, replan, route to human review, or stop for manual investigation.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Relay is a production-shaped reliability harness for agent actions against mutable business systems. It injects failures around a synthetic source-of-record adapter, reads state back after attempted mutations, reconciles intended versus observed effects, and decides whether to complete, retry safely, replan, route to human review, or stop for manual investigation.檢視完整 README ↗