akitaonrails/ai-memory：README 來源編輯指南

akitaonrails/ai-memory 的 README 將專案描述為「Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors」。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：> Long-term memory for AI coding agents. Quit Claude Code mid-task, > start OpenAI Codex in the same directory, continue without > re-explaining the architecture, the failed approaches, or the open > questions.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Key features」與相關條目，可以先判斷它是否處理你的實際問題：Opt-in managed workstreams. ai-memory run claude, then ai-memory run。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：Zero-friction lifecycle capture. Hooks fire-and-forget bounded,。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「What it is」等段落。可確認的線索包括：LLM coding agents lose context when a session ends. ai-memory gives them a shared, persistent wiki compiled from sanitized lifecycle observations. When a session ends, relevant observations become a coherent summary;。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： # 1. Install the ai-memory CLI wrapper (a small shell script that # runs the binary inside docker with your $HOME mounted). This is # the only thing that needs to live on the host filesystem. mkdir -p ~/.local/bin wrapper_tmp="$(mktemp -d)" trap 'rm -rf "$wrapper_tmp"' EXIT wrapper_base=https://github.com/akitaonrails/ai-memory/releases/latest/download/ai-memory-wrapper curl -fsSL "$wrapper_base" -o "$wrapper_tmp/ai-memory-wrapper" curl -fsSL "$wrapper_base.sha256" -o "$wrapper_tmp/ai-memo 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「What it is」，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「What it is」段落提到：The wiki is plain markdown in a git repo - grep-able, openable in Obsidian, backed up with rsync. No vector database to babysit, no writenote ceremony, no manual context-loading. The full design is in docs/ARCHITECTURE.md.。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：Per-repository capture exclusions. A nearest-marker [capture]。