Free resources to help you deploy and manage local AI infrastructure.
Ollama + Open WebUI Docker Compose
Production-ready docker-compose.yml with Ollama and Open WebUI. Includes GPU support, persistent storage, health checks, and telemetry disabled.
GPU Comparison Cheat Sheet
Side-by-side comparison of consumer GPUs for local AI: VRAM, pricing, inference speed, power draw, and model compatibility. Includes a quick decision guide and electricity cost estimates.
Local AI Security Checklist
Hardening checklist for self-hosted AI deployments covering network security, container isolation, authentication, data protection, and monitoring.
