23blocks-OS/ai-maestro：README 来源编辑指南

23blocks-OS/ai-maestro 的 README 将项目描述为"AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between computers and locations"。本文只整理仓库能直接核验的内容，不把星标、Fork 或宣传语当成质量证明。README 在"AI Maestro"下的说明是：I was running 35 AI agents across multiple terminals and became the human mailman between them. So I built AI Maestro.。这给出的首先是项目边界，而不是已经完成的生产验证。

从 README 的"The Story"和相关条目看，读者可以先判断它是否解决自己的具体问题：Multi-machine from day one , Peer mesh network with no central server. Nobody else does this.。如果你的目标与这段说明不一致，就不应仅凭项目热度采用它。这里保留原项目名、命令和组件名，方便回到一手来源核对。 README 还列出了另一条可核对的信息：Works with any AI agent , Claude Code, Codex, Aider, Cursor, OpenClaw, Hermes, Droid, or any terminal-based agent. We don't lock you in.。这类原文条目可以帮助读者设计试运行步骤，但不能代替自己的环境测试。

README 把工作方式分散写在"The Story"等段落中。可确认的线索包括：I gave an AI agent a real task , not autocomplete, a real engineering problem. It checked the code, read the logs, queried the database, and came back with the answer. That was the moment. This thing can actually work.。这篇整理没有把未写出的架构、性能或安全边界补成结论；真正的运行链仍应结合仓库目录、配置文件和版本标签检查。

第一次安装应从 README 给出的入口开始。当前可复核的命令是： curl -fsSL https://raw.githubusercontent.com/23blocks-OS/ai-maestro/main/scripts/remote-install.sh | sh 如果仓库没有提供命令，本文不会替它编造安装步骤，而是建议先打开 README 的"The Story"部分，确认系统依赖、默认端口和首次初始化动作。

日常使用的细节取决于项目实际文档。README 的"The Story"段落提到：Within a week I was running 35 agents across terminals. They were productive, but they couldn't talk to each other. I became the human message bus , copying context from one terminal, pasting into another.。对于配置文件、环境变量、权限和数据目录，当前稿只记录来源明确的部分；未写明的默认值必须在测试环境中验证，并保留可回滚的配置副本。 同一部分还提到：Agents that communicate , The Agent Messaging Protocol (AMP) lets agents coordinate directly. You orchestrate, they collaborate.。