# Creating your own HomeLAB: Quad-Architecture (v3.6)
###
Welcome to **HomeLAB v3.6**, 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.
###
1. **Abacus.ai Pro Package**: Sign up for the Pro package at [Abacus.ai](https://abacus.ai) for access to **Kimi k2.5**, **Antigravity Pro**, and **Gemini 3 Flash**.
28. **DeepSeek API Key**: (Optional) For specialized reasoning tasks.
3. **Antigravity AI**: The orchestrator is managed by **Antigravity**. Download: [https://antigravity.google/download](https://antigravity.google/download).
###
- **Sovereign Intelligence Feed**: A new dedicated ticker for real-time 𝕏/Telegram sentiment analysis. Pivoted to Telegram public previews for 100% auth-free resilience.
- **Massive Code Generation**: All models (Cloud & Local) are now tuned for **16,384 tokens**, allowing for 1,500+ lines of continuous code generation in a single pass.
- **Dual-Input "Letter Box" Layout**: A dedicated Top Panel for Cloud (Strategy/Review) and a Bottom Panel for Local (Privacy Zone).
- **Non-Blocking Execution**: No more waiting. Hose the cloud with strategy while Gemma 3 audits your local logic.
###
- **Shared Blackboard Protocol**: All departments (Strategy, Review, Local) now read and write to a single source of truth (`BLACKBOARD.md`).
- **Zero Copy-Paste**: Context is automatically shared. Ask Strategy to plan, then simply tell Local to "Read the Blackboard and proceed."
- **Project Lifecycle Management**: Use the new `
###
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".
###
HomeLAB v3.6 uses a resilient "N+1" redundancy system. All cloud departments now feature **Hyper-Fallback** to your local hardware:
- **Strategy Dept**: `Gemini 3.1 Flash` (Primary/Ticker) ➔ `Gemini 2.5` (Fallback) ➔ `Local`.
- **Review Dept**: `Kimi k2.5` (Primary) ➔ `Kimi k2.0` (Fallback) ➔ `Local`.
- **Local Dept**: `Gemma 3:27b` (Primary) ➔ `Gemma 3:12b` (Fallback).
###
- **Context Memory**: Automatically summarizes conversation history every 10 exchanges, allowing for massive "infinite" logic retention without crashing the context window.
- **Redundancy Logic**: Cloud failures (timeouts, connection issues) automatically route to the **Sovereign Stack** (Local Gemma 3).
- **VRAM Management**: High-speed "Purge" logic for local models, optimized for AMD RX 7900 XTX (ROCm) and NVIDIA alike.
- **Visual Heartbeat**: Real-time "Neural Bridge: ACTIVE" status in the GUI header with automatic startup confirmation log.
---
*Note: This is a sovereign AI workstation. If you don't want to subscribe to cloud providers, 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!*