rohitg00/agentmemory：README 來源編輯指南

rohitg00/agentmemory 的 README 將專案描述為「#1 Persistent memory for AI coding agents based on real-world benchmarks」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「README」下寫到：Your coding agent remembers everything. No more re-explaining. Built on iii engine Persistent memory for Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, pi, OpenCode, and any MCP client.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Codex CLI (Codex plugin platform)」與相關條目，可以先判斷它是否處理你的實際問題：6 lifecycle hooks: SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, PreCompact, Stop。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：@agentmemory/mcp as an MCP server (proxies all 54 tools when AGENTMEMORYURL points at a running agentmemory server; falls back to 7 tools locally when no server is reachable)。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「Install」等段落。可確認的線索包括：On Windows the fast path is WSL2. Native Windows engine setup is manual (about 10 to 20 minutes) and agentmemory connect is currently unsupported there. See the Windows notes below for the step-by-step.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： npm install -g @agentmemory/agentmemory # once , bare `agentmemory` on PATH # If you hit EACCES on macOS/Linux system Node installs, retry with: # sudo npm install -g @agentmemory/agentmemory agentmemory # start the memory server on :3111 agentmemory demo # seed sample sessions + prove recall agentmemory demo --serve # one command: boot server, run demo, tear down (no second terminal) agentmemory conne 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「Retrieval Accuracy」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「Install」段落提到：Heads-up , npx caches per version. If a bare npx @agentmemory/agentmemory serves an older release, force the latest with npx -y @agentmemory/agentmemory@latest, or clear the cache once with rm -rf /.npm/npx (macOS/Linux;。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：8 invocable skills: /recall, /remember, /session-history, /forget, /recap, /handoff, /commit-context, /commit-history, plus 7 reference skills the agent loads on demand (MCP tools, REST API, config, agents, hooks, architecture, and the。