Ollama
A tool for running AI models locally. Free, private, fast.
Why it matters
Ollama democratizes AI — run capable models on your hardware for free. No API keys, no data leaving your machine.
In practice
We run Ollama with llama3.2 on Hetzner. It handles 80-95% of LLM calls for $0/month.
Related terms
Local Model
An AI model running on your own server (e.g., via Ollama), keeping data private and costs near zero.
Fallback
An alternative approach when the primary method fails (e.g., Ollama fails, Claude API takes over).
n8n-First Principle
A design philosophy: every repeatable task is a workflow, not an AI call. AI is the last resort.
LLM (Large Language Model)
A large language model like Claude, GPT, or Gemini. The "brain" that understands and generates language.