LLM Vision

Home Assistant integration that uses multimodal AI to analyze camera images and video.

Pluginfree

LLM Vision is a Home Assistant integration that uses multimodal AI models to analyze images, video, live camera feeds, and Frigate events, answering questions and generating descriptions of what a camera captured. It remembers people, pets, and objects, keeps a timeline of events for dashboards, and works with providers including OpenAI, Anthropic, Google Gemini, and local Ollama models. It is aimed at Home Assistant users who want more useful, descriptive camera notifications than plain motion alerts.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of LLM Vision - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim LLM Vision to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether LLM Vision (or something else) actually fits.

Try a problem