A Home Assistant integration that brings a generative AI agent into your smart home. Talk to your home, create automations in plain English, analyze camera footage, and get proactive alerts — all powered by your choice of cloud or local LLMs. HGA is a single integration that gives you conversational control over every HA entity, camera understanding with face recognition, long-term semantic memory, and the Sentinel anomaly engine.
| Feature | What it does |
|---|---|
| Conversational control | Talk to your home in natural language. Turn things on, check status, ask questions. |
| Automation creation | Describe what you want in chat and the agent writes and registers the HA automation. |
| Camera & image analysis | Ask the agent what it sees in any camera. Proactive motion-triggered analysis with anomaly detection. |
| Sentinel anomaly detection | Deterministic rules watch for security and safety issues (unlocked locks, open entries, unknown people) and alert your phone. Optional LLM-powered triage and rule discovery. |
| Face recognition | Identify people in camera frames and personalize alerts. |
| Long-term memory | Semantic search over past conversations. The agent remembers your preferences and context. |
| Streaming responses | First tokens appear word-by-word in the HA conversation UI — no waiting for the full response. |
| Cloud and edge models | Use OpenAI, Gemini, Anthropic, or run everything locally with Ollama or any OpenAI-compatible server. |
| Requirement | Notes |
|---|---|
| Home Assistant | 2025.5.0 minimum; 2026.4.0+ for streaming responses |
| HACS | Required for the recommended install path; manual install is also supported |
| PostgreSQL with pgvector | Provided as a bundled HA app (step 1 below) |
| Model provider | At least one of: OpenAI, Gemini, Anthropic, Ollama, or any OpenAI-compatible server |
| Edge GPU server (optional) | Ollama, vLLM, llama.cpp, or LiteLLM for local model serving |
| face-service (optional) | An external service required only for face recognition in camera analysis |
Get the basic conversational agent running in seven steps. See the full installation guide for optional apps (edge models, face recognition).
1. Install the PostgreSQL with pgvector app.
Requires Home Assistant OS or Supervised (apps are not available on HA Container or Core).
Click the button below to add the repository, then install and configure the app per its documentation.
If the button doesn't work, add the repository manually: Settings → Apps → App Store → ⋮ → Repositories, enter
https://github.com/goruck/addon-postgres-pgvector, then search for and installpostgres_pgvector.
2. Install Home Generative Agent from HACS.
3. Restart Home Assistant.
4. Add the integration: Settings → Devices & Services → Add Integration → search Home Generative Agent → complete the initial instruction screen.
5. Open the integration page and click + Setup. Enable the features you want (Conversation is on by default) and complete the database configuration step.
6. Add a Model Provider: on the integration page click + Model Provider and configure OpenAI, Ollama, Gemini, Anthropic, or any OpenAI-compatible endpoint.
7. Set as your voice assistant: Settings → Voice Assistants → select Home Generative Agent as the conversation agent.
You can now open the HA Assist panel and start talking to your home.
| Guide | Contents |
|---|---|
| Installation | HACS install, manual install, optional apps (Ollama, face recognition) |
| Configuration | Model providers, features, Tool Retrieval (RAG), LLM API, STT, YAML mode, Critical Action PIN |
| Sentinel | Anomaly detection pipeline, built-in rules, triage, baseline, blueprints, services API, health sensor |
| Camera Entities | Image and sensor entities, dashboards, automations, proactive video analysis, face recognition |
| Architecture | LangGraph agent, model tiers, context management, streaming, latency, tools |
| Contributing | Dev setup, Makefile reference, dependency workflow |
User asked: "Remind me every 30 minutes if the litter box waste drawer is over 90% full." Agent wrote and registered the automation.
alias: Check Litter Box Waste Drawer
triggers:
- minutes: /30
trigger: time_pattern
conditions:
- condition: numeric_state
entity_id: sensor.litter_robot_4_waste_drawer
above: 90
actions:
- data:
message: The Litter Box waste drawer is more than 90% full!
action: notify.notify
User asked: "When did the front porch light turn on today?" Agent queried the HA history database and summarized the results.
User asked: "How much energy did the fridge use today?" Agent pulled sensor history and gave a plain-English summary.
User asked in a later conversation: "always prepare the home for my arrival at night" Agent retrieved the relevant context from long-term memory and then built the automation, remembering that the user arrives home around 7:30 PM.
User asked: "Are there any packages at the front gate?" Agent analyzed the live camera and confirmed two boxes visible.
If you want to contribute to this, please read the Contribution guidelines.