Local & private AI for automation
Local models used inside scheduled jobs and workflows, such as triaging, tagging and summarizing, where cheap repeated calls matter more than peak intelligence.
Rebel BitesSelf-hosted bookmarks that tag themselves with local AI (Karakeep)
Karakeep (formerly Hoarder) runs on a Debian LXC, and gemma3:4b in Ollama tags each bookmark. Getting reliable tags from a small model takes one key setting.
Hybrid workflow: local for private and repetitive, cloud for hard
A Linux sysadmin stopped trying to replace cloud LLMs. Ollama now handles private docs, overnight article summaries and VS Code autocomplete.
Self-hosted AI email assistant on Linux (n8n + Ollama)
Classifies IMAP mail with llama3.1:8b, routes it, saves reply drafts and extracts action items as JSON. Reports 85-95% classification accuracy.
Email triage and morning digest with a local Ollama model (n8n)
Classifies each email as URGENT, REPLY_TODAY, FYI or JUNK using gemma4:e4b, sends urgent alerts and builds a grouped morning digest.
Auto-label Gmail and draft replies with a local model (n8n)
Sorts unread Gmail into six categories with Ollama, applies labels, drafts replies for urgent mail and logs everything to Sheets, with zero paid API costs.