Guides
Hands-on walkthroughs for AI infra, agents, and local LLMs — written for engineers, not analysts.
Category
Difficulty
Running a Hermes Agent Locally
Set up a function-calling Hermes agent with tool registration and optional memory backend in under 20 minutes.
vpsHetzner VPS Setup for AI Workloads
Rent and harden a Hetzner Cloud VPS for running local LLMs, agents, or a private inference gateway.
local-llmRun Local LLMs on Mac (Apple Silicon)
Use Ollama and Open WebUI to run quantized language models locally on M1/M2/M3 Macs with Metal acceleration.
notebooklmNotebookLM: From Zero to Useful in 15 Minutes
Load your documents into NotebookLM and start getting answers, summaries, and audio overviews immediately.