Home Ai Factory

Home AI Factory

**Self-hosted AI infrastructure combining Claude Code + Letta persistent memory + intelligent model routing + local GPU inference.**

A personal "AI command center" that gives you:

• Persistent memory across Claude Code sessions via Letta
• Intelligent model routing via LLMRouter - automatically picks the right model for each task
• Local inference on RTX 3090 via Ollama (free compute for simple tasks)
• Vector search + graph database via PostgreSQL + pgvector + Apache AGE
• Document ingestion pipeline via CocoIndex
• Secure mesh networking via WireGuard

Architecture

┌─────────────────────────────────────────────────────────────────────────────────┐
│                           YOUR WORKSTATION (MacBook)                             │
│  ┌─────────────────────────────────────────────────────────────────────────┐    │
│  │                      Claude Code + Letta Memory Proxy                    │    │
│  │  - Opus 4.5 reasoning (via Claude Max subscription - FREE inference)     │    │
│  │  - GPT-4o/o1 (via GPT Pro subscription - FREE inference)                 │    │
│  │  - Persistent memory across ALL sessions                                 │    │
│  │  - Full filesystem + SSH access                                          │    │
│  └─────────────────────────────────┬───────────────────────────────────────┘    │
└────────────────────────────────────┼────────────────────────────────────────────┘
                                     │ WireGuard VPN (10.0.0.0/24)
                                     ▼
┌─────────────────────────────────────────────────────────────────────────────────┐
│                           GPU SERVER (RTX 3090 PC)                               │
│                                                                                  │
│  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────────┐                  │
│  │  Letta Server   │  │   LLMRouter     │  │     Ollama      │                  │