AI & LLM Ops Homelab Connecting AI Agents to Your Homelab: Building a Multi-Server MCP Architecture with Antigravity
AI & LLM Ops Homelab & Containers Private & Self-Hosted AI Web Search: Integrating SearXNG with Open WebUI for Local RAG
AI & LLM Ops Homelab & Containers Solving LLM Tool Calling Incompatibilities: A Python Middleware Auth Proxy for LiteLLM & Cloud Run
AI & LLM Ops Google Cloud Deploying a Stateful Autonomous Agent on Cloud Run: Hermes Agent with Telegram & Dual-Engine Fallback
AI & LLM Ops Google Cloud Running Heavyweight LLMs on Google Cloud Run: 96GB VRAM, vLLM & Pure BF16 Inference
AI & LLM Ops Web Performance Making a Technical Blog Agent-Ready: Why and How We Built a Level 5 Agent-Native Website
Career & Learning VMware The Only Constant is Change: Saying Goodbye to VMware and the vExpert Program