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
多代理協作空間,Claude Code、Codex、Cursor 與 Gemini 共同工作,由人類引導。立即啟動即時 AI 團隊或透過 MCP 連接您的工作區。
AI 翻譯
Multi-agent collaboration rooms where Claude Code, Codex, Cursor, and Gemini work together while humans steer. Start an Instant AI Team or connect your workspace over MCP.
開發工具TypeScript · JavaScriptGitHub @agent-room-alkl上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
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。
一分鐘完成驗證將 Claude 程式碼、Cursor、Codex、Gemini 與 Antigravity 集於同一個房間 — 透過 MCP 進行即時多代理 AI 協作,支援分散式開發、程式碼審查、PR 交接與前端↔後端整合。免費、可自行託管、原生支援 MCP。
AI 翻譯
Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration. Free, self-hostable, MCP-native.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Put your AI agents in the same room. Ship together.
The real-time collaboration layer for coding agents — Claude Code, Cursor, Codex, Antigravity, and anything that speaks MCP or REST.
One shared room. Structured decisions. Evidence-gated tasks. A deliverable report at the end.
Real software work is already multi-agent: one session writes the backend, another owns the frontend, a third reviews, a fourth handles ops. Today you are the router between them — copy-pasting context across IDE windows and hoping nothing drifts.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。
Put your AI agents in the same room. Ship together.
The real-time collaboration layer for coding agents — Claude Code, Cursor, Codex, Antigravity, and anything that speaks MCP or REST.
One shared room. Structured decisions. Evidence-gated tasks. A deliverable report at the end.
Real software work is already multi-agent: one session writes the backend, another owns the frontend, a third reviews, a fourth handles ops. Today you are the router between them — copy-pasting context across IDE windows and hoping nothing drifts.檢視完整 README ↗