# Creating your own HomeLAB: Quad Architecture (v3.3)

### Introduction
Welcome to **HomeLAB v3.3**, the "Sovereign Stack" AI Orchestrator. This version marks a major upgrade to the **Parallel Engine Architecture**, giving you a dual-input workstation that can process Cloud and Local tasks at the same time.

### Prerequisites
1. **Abacus.ai Pro Package**: Sign up for the Pro package at [Abacus.ai](https://abacus.ai) for access to **Gemini 3 Flash** and **Kimi k2.5**.
2. **Antigravity AI**: The orchestrator is managed by **Antigravity**. Download: [https://antigravity.google/download](https://antigravity.google/download).

### New in v3.3: Parallel Processing
- **Dual-Input "Letter Box" Layout**: A dedicated Top Panel for Cloud (Strategy/Review) and a Bottom Panel for Local (Privacy Zone).
- **Non-Blocking Execution**: You no longer have to wait for the local model to finish. You can "hose" the cloud with strategy questions while Gemma 3 is deep in thought on a local audit.
- **Turbo-Dev Workflow**: Write code on the cloud and review it on local simultaneously.

### Installation Steps
1. **Create a Folder**: Create a folder on your computer (D: or C: drive) called `VAULT-AI`.
2. **Download & Unzip**: Download this HomeLAB Zip and unzip it into `VAULT-AI`.
3. **Launch Antigravity**: "Add Folder to Workspace" ➔ Select `VAULT-AI`.
4. **Automated Setup**: Ask Antigravity: "Set up my HomeLAB".

### The Quad Architecture (Parallelized)
HomeLAB v3.3 uses a resilient "N+1" redundancy system:
- **Strategy Dept**: `Gemini 3 Flash` (Primary) ➔ `Gemini 2.5 Flash` (Fallback).
- **Antigravity Dept**: `Gemini 3.1 Pro` (Primary) ➔ `Gemini 3 Pro` (Fallback).
- **Review Dept**: `Kimi k2.5` (Primary) ➔ `Kimi k2.0` (Fallback).
- **Local Dept**: `Gemma 3:27b` (Primary) ➔ `Gemma 3:12b` (Fallback).

### Smart Memory & Safety
- **Context Memory**: Automatically summarizes conversation history every 10 exchanges, allowing for massive "infinite" logic retention without crashing the context window.
- **Auto-Backup**: The system automatically zips its own core engine files into the `/backups` folder periodically, ensuring your custom logic is never lost.
- **VRAM Management**: High-speed "Purge" logic for local models, optimized for AMD RX 7900 XTX (ROCm) and NVIDIA alike.

---
*Note: This is a sovereign AI workstation. If you don't want to subscribe to Abacus.ai, you can still run the Local Gemma 3 models for FREE as no API_KEY is required. Enjoy the dual-engine power of the Quad!*