Vibe Coding Discoverhome-generative-agent
View on GitHubAI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts. Cloud LLMs or fully local via Ollama.
Home Assistant integration with a LangGraph agent that controls entities, writes real HA automations from plain English, analyzes cameras with face recognition, and runs local pgvector memory plus a deterministic Sentinel anomaly/security engine. Works with OpenAI, Gemini, Anthropic, or fully local Ollama.
Use Cases
Control Home Assistant entities in natural languageGenerate and register HA automations from a plain-English descriptionAnalyze camera frames and video for objects, people, and anomaliesSend proactive motion/security alerts to a phoneIdentify known and unknown people via face recognitionRun an on-demand Home Assistant security auditRecall user preferences through long-term semantic memoryRun fully local with Ollama or any OpenAI-compatible serverVoice pipeline STT/TTS for HA AssistDeterministic Sentinel rules for locks, entries, and sensors
Built With
- Language
- Python
- Frameworks
- LangGraph · LangChain · Home Assistant · Ollama · vLLM · llama.cpp · LiteLLM · pgvector · PostgreSQL · Speaches · faster-whisper
Tags
home-assistant · smart-home · ai-agent · langgraph · anomaly-detection · computer-vision · face-recognition · pgvector · semantic-memory · local-llm · ollama · voice-assistant · hacs · rag · automation · proactive-alerts