Preview coming soon
Local RAG AI Agent
Cole Medin demonstrates a full cloud deployment of a local AI stack, integrating LLM (Ollama), databases (Supabase, Qdrant), automation agents (n8n with Flowise), local search (SearXNG) and a user interface (Open WebUI). The setup uses Docker containers, secured endpoints via Caddy, and detailed firewall/DNS configurations for subdomains. This free, open-source system extends an original n8n template and is available on GitHub for immediate use.
Integrations
Tags
One-time purchase
Related automations
Sales Assistant Build
This comprehensive workflow by Nolan Harper uses n8n to deliver a 24/7 AI sales assistant tailored for automating lead capture and personalized follow-up. The...
Publish to 9 Social Platforms
This system is an automated workflow that reads content details from a Google Sheet, extracts media from Google Drive, and uses API calls to a dedicated social...
Parent Agent
This workflow demonstrates a multi-agent architecture where a parent agent communicates with child agents to perform tasks like story generation. It details...