vxcontrol/pentagi：README 来源编辑指南

vxcontrol/pentagi 的 README 将项目描述为"Fully autonomous AI Agents system capable of performing complex penetration testing tasks"。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"PentAGI"下的说明是：> Join the Community! Connect with security researchers, AI enthusiasts, and fellow ethical hackers. Get support, share insights, and stay updated with the latest PentAGI developments.。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"Features"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：Fully Autonomous. AI-powered agent that automatically determines and executes penetration testing steps with optional execution monitoring and intelligent task planning for enhanced reliability.。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：Secure & Isolated. All operations are performed in a sandboxed Docker environment with complete isolation.。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"System Context"等段落中。可确认的线索包括：The chain summarization system manages conversation context growth by selectively summarizing older messages. This is critical for preventing token limits from being exceeded while maintaining conversation coherence.。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： graph TB subgraph Core Services UI[Frontend UI<br/>React + TypeScript] API[Backend API<br/>Go + GraphQL] DB[(Vector Store<br/>PostgreSQL + pgvector)] MQ[Task Queue<br/>Async Processing] Agent[AI Agents<br/>Multi-Agent System] end subgraph Knowledge Graph Graphiti[Graphiti<br/>Knowledge Graph API] Neo4j[(Neo4j<br/>Graph Database)] end subgraph Monitoring Grafana[Grafana<br/>Dashboards] VictoriaMetrics[Vi 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"Table of Contents"部分，确认系统依赖、默认端口和首次初始化动作。