Home AI Factory — AI skill for Claude Code
Self-hosted AI Factory: Claude Code + Letta Memory + VectorGraph + Local RTX 3090 Inference.
How to install Home AI Factory
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jmanhype/home-ai-factory and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Home AI Factory does
Self-hosted AI Factory: Claude Code + Letta Memory + VectorGraph + Local RTX 3090 Inference. Personal AI command center with persistent memory.
Alternatives in AI
- Invisible Dots — Open-source, self-hosted alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and Claude Cowork 31.8k ★
- Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
- Phantom — An AI co-worker with its own computer 1.3k ★
README
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 │ │
Related Skills
HomeAILab
Home AI inference lab running Qwen3.8 across RTX 5090, RTX 3090, and DGX Spark with vLLM, llama.cpp, custom Go
Recallium
Recallium is a local, self-hosted universal AI memory system providing a persistent knowledge layer for develo
1Helm
Self-hosted home for durable AI employees: one resident, one private computer, compounding memory and skills,
Gaffer
Self-hosted AI coding factory — sandboxed agents deliver tickets to merged code, gated by a human in a dashboa
Recollect
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessi
MxLore
Self-hosted MCP server for AI coding assistants. Persistent knowledge base with 45 tools, 12 skills, instituti
Related Agents
Homelab Platform
Home-lab site reliability and platform operations for Linux hosts, VMs, container stacks, networking, storage,
Homelab Engineer
Home-lab site reliability and platform operations for Linux hosts, VMs, container stacks, networking, storage,
Hermes Agent
Integration file for a Hermes-style personal agent system. Use when a Hermes deployment (a self-hosted assista