lumina-homelab - Defensive-focused AI homelab Claude Code plugin —

项目说明

lumina-homelab

Defensi AI homelab — a Claude Code plugin. Castle Doctrine security, federated local inference, autonomous go.

![Alpha]()

> Status: Pre-alpha. Acti. APIs unstable. If you're here before 2026-05-01, you're early.

What this is

A Claude Code plugin that turns your homelab into a defensive AI perimeter. Ships with:

What this is NOT

Installation

Requires: Python ≥3.10, Claude Code CLI, lumina-oss>=0.1.0

First run will prompt for user_config : homelab IP, optional LiteLLM endpoint, Castle Doctrine mode (LOCKDOWN / PATROL / OPEN).

Architecture

Upstream dependency: lumina-oss — MIT-licensed framework pro HUD, health domain scanner, and (coming soon) bus/LLM routing/knowledge/go primitives.

Castle Doctrine

Four zones, four responsibilities:

| Zone | Responsibility | Components |
|---|---|---|
| KEEP | Core agent + skills | skills/, agents/ |
| MOAT | Perimeter defense | hooks/ — COMPUSEC, ESTOP, @HK-47 |
| ARMORY | Tools + utilities | bin/ CLI executables |
| WATCHTOWER | Obser | monitors/ — health checks, syphon sweeps |

Status

License

MIT. See LICENSE.

Contributing

Issues and PRs welcome. This is a li; expect APIs to shift before v1.0.

---

*Cedarbrook Financial Services LLC. Built for the Apr 30 2026 gate.*

项目信息

开发语言：Python

Star 数：1

技术要点

该项目属于防护思路方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Defensive-focused AI homelab Claude Code plugin — Castle Doctrine security, local-first inference, autonomous governance. Apr 30 2026 Gate.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。