Quest Log

• Tunneling Local LLMs to the Cloud with Tailscale

  5/24/2025

  Hooked up my local LLMs (running with Ollama) to my VPS using Tailscale, letting apps like n8n and other web tools query them over HTTPS. It's been great for cost-effective testing and small-scale workloads before pulling in heavyweight APIs.

  LLMsVPSDev ToolsAutomationn8n

• Self-Hosting n8n on a VPS with PostgreSQL, Docker, and SSL

  5/10/2025

  I self-hosted n8n on a VPS to ditch execution limits and get full control without the monthly price tag. PostgreSQL for multi-user support, Docker for easy deployment and updates, and a polished subdomain setup — here's how it came together.

  Automationn8nDevOpsDockerVPSPostgreSQLDatabases

• Built My Own AI Server at Home — Here’s the Setup and Why It Rocks

  4/26/2025

  Set up a custom AI server on my home network with a Ryzen 9950X3D, 64GB DDR5 RAM, and an RTX 5090. It's running ComfyUI, OpenWebUI, and Ollama, reachable via static IP and reverse proxy. Here's a breakdown of the build and lessons from the setup.

  AIDevOpsLLMsVPSBackend