Local AI and n8n setup

Mac Mini AI stack that survives reboots.

A diagnostic for Ollama, n8n, AnythingLLM, ChromaDB, Telegram bots, launchd persistence, and written handoff on macOS.

Setup risk map

AreaWhat I check before touching the machine
PersistenceWhether n8n, ChromaDB, AnythingLLM, and the Telegram workflow should run through Docker Compose, LaunchAgents, or LaunchDaemons.
Ollama on M-seriesModel choice, memory footprint, GPU use, context length, and whether workloads interfere with the desktop session.
NetworkLAN-only access, webhook exposure, tunnel choice, firewall rules, and Telegram bot callback path.
Data storageWhere ChromaDB, n8n data, model files, backups, and logs live so they are recoverable.
ValidationOne end-to-end test: Telegram message -> n8n -> local model/RAG -> response -> log.

$29 diagnostic deliverable

Request diagnostic