
Phil and Rohan explore practical AI applications for Home Assistant, discussing various tools and setups.
Phil and Rohan go deep on practical AI for Home Assistant. We cover LLM Vision for doorbell and perimeter alerts, HACS add‑ons like AI Agent and AI Suggester, and using GitHub Copilot to generate YAML automations. Rohan shares his Ollama + LiteLLM routing setup and why private cloud models might beat pay‑per‑token APIs. Phil battles OpenClaw (aka MoltBot/Claude Bot) to control lights via MCP Watch this episode on YouTube Show notes for this episode are available at https://homeassistant.fm/HA225 Support the Podcast Get early-access to episodes and an ad-free feed by supporting our Patreon. https://homeassistant.fm/patreon Share your story We wouldn't be able to do this podcast without community members and home automation enthusiasts sharing their stories. To register your interest to come share your home automation journey, head over to homeassistant.fm and click share your story . Chapters 00:00:00 - Intro 00:02:02 - Rohan’s AI stack today 00:09:00 - HA’s built-in AI + Copilot 00:18:00 - HACS: AI Agent & Suggester 00:26:24 - LLM Vision in practice 00:37:00 - OpenClaw, MCP, and gotchas 00:47:00 - Do we need agents? Use cases 00:51:00 - Costs, feedback, and outro This episode…
Host: Phil
Guest: Rohan
Home Assistant Cloud by Nabu Casa
Organizations: Home Assistant, GitHub, Zooz
Products: OpenClaw, MoltBot, Claude Bot, AI Agent, AI Suggester, Ollama, LiteLLM
Explore listener stats, chart rankings, contacts and more on the Home Assistant Podcast podcast page.