valentinfrlch/ha-llmvision

Health v2 · maintenance only

Adoption not part of the score

1440 stars · 139 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LLM Vision is a Home Assistant integration (installed via HACS) that uses multimodal large language models to analyze images, videos, live camera feeds, and Frigate events. It builds a timeline of analyzed events, updates sensors from extracted data, and supports many providers including OpenAI, Anthropic, Google Gemini, Ollama, and any OpenAI-compatible endpoint.

Use cases

• analyze who is at my front door camera
• get notified when a package is delivered
• describe what happened in a cctv clip
• track people and pets seen by home cameras
• build a timeline of camera events in home assistant
• run local vision models on camera feeds for privacy
• create automations triggered by what a camera sees

When to choose

• you use Home Assistant and want AI-powered analysis of cameras, images, or videos
• you want provider flexibility including fully local models via Ollama or LocalAI
• you want event timelines and sensor updates driven by visual data

When to avoid

• you don't use Home Assistant
• you need real-time object detection without LLM inference costs or latency
• you want a standalone computer-vision pipeline outside a smart-home context

Facets

plugin · maturity active

machine-learning computer-vision llm-inference image-processing video-processing alerting workflow-automation iot artificial-intelligence computer-vision self-hosted python home-assistant hacs multimodal-llm cctv frigate camera-analytics timeline home-automation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="valentinfrlch/ha-llmvision")