尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
依最近已完成的 8 小時觀測回合間的 GitHub 星號增量排序
PGX — Lightweight Postgres for AI agents. Written in Rust. Thousands of isolated databases in one runtime. 🐘
翻譯準備中
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。
一分鐘完成驗證正在載入完整 README。 以下為已儲存的摘錄。
A comprehensive system for collecting, normalizing, and aggregating LLM benchmark scores across 15+ benchmark sources. This tool creates a unified dataset of AI model performance metrics from diverse evaluation platforms.
ai-bench solves the problem of fragmented AI model benchmarking: different organizations run benchmarks independently, each with their own model naming conventions, scoring formats, and update schedules. This project aggregates all these scores into a single, normalized JSON file (llm.json) where: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。
A comprehensive system for collecting, normalizing, and aggregating LLM benchmark scores across 15+ benchmark sources. This tool creates a unified dataset of AI model performance metrics from diverse evaluation platforms.
ai-bench solves the problem of fragmented AI model benchmarking: different organizations run benchmarks independently, each with their own model naming conventions, scoring formats, and update schedules. This project aggregates all these scores into a single, normalized JSON file (llm.json) where:檢視完整 README ↗