LOCAL AI & HOME INFRASTRUCTURE

Practical AI.
Local infrastructure.

Documenting the design, configuration, and operation of my homelab, with a focus on local AI, self-hosted services, and home automation.

Explore the projects About the lab

BUILD GUIDES · CONFIGURATION · TECHNICAL NOTES

THE HOME LABFIG. 01 / OVERVIEW

JOE / LOCAL NETWORK● ● ●

COMPUTELocal AI & experiments

STORAGEData & application storage

NETWORKPrivate network services

▥▥▥●

COMPUTE / STORAGE / NETWORK↳

Self-hosted infrastructure

Areas of focusLocal AI/Home servers/Automation/Documentation

01 / THE PROJECTS

Recent projects

All projects

in progress

LOCAL AI / COMPUTE

Hermes Agent on a Mac mini with Ollama

Running Hermes Agent on an Intel Mac mini with GPU inference on Unraid. A restricted Linux account, Tailscale, an authenticated Nginx proxy, and nftables limit access to the Ollama backend.

in progress

LOCAL AI / COMPUTE

Local AI Server Build

Local AI inference on Unraid 7.2.7 with a Ryzen 5 5600G, 32 GB DDR4, and an NVIDIA Tesla V100 PCIe 32 GB. The GPU runs at a 150 W power limit with a custom 3D-printed fan shroud.

Practical AI.Local infrastructure.

Recent projects

Hermes Agent on a Mac mini with Ollama↗

Local AI Server Build↗

Practical AI.
Local infrastructure.

Hermes Agent on a Mac mini with Ollama

Local AI Server Build