nanocoai/nanoclaw：README 來源編輯指南

nanocoai/nanoclaw 的 README 將專案描述為「A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK」。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：An AI assistant that runs agents securely in their own containers. Lightweight, built to be easily understood and completely customized for your needs.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「What It Supports」與相關條目，可以先判斷它是否處理你的實際問題：Flexible isolation , connect each channel to its own agent for full privacy, share one agent across many channels for unified memory with separate conversations, or fold multiple channels into a single shared session so one conversation。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：Multi-channel messaging , WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend. Installed on demand with /add- skills. Run one or many at the same time.。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「Why I Built NanoClaw」等段落。可確認的線索包括：NanoClaw provides that same core functionality, but in a codebase small enough to understand: one process and a handful of files. Agents run in their own Linux containers with filesystem isolation, not merely behind permission checks.。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： git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2 cd nanoclaw-v2 bash nanoclaw.sh 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「Quick Start」，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「Quick Start」段落提到：nanoclaw.sh walks you from a fresh machine to a named agent you can message. It installs Node, pnpm, and Docker if missing, registers your Anthropic credential with OneCLI, builds the agent container, and pairs your first channel。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-agent workspace , each agent group has its own CLAUDE.md, its own memory, its own container, and only the mounts you allow. Nothing crosses the boundary unless you wire it to.。