# Home LLM

A Home Assistant integration and family of small fine-tuned models that let a completely local language model understand voice or chat requests and control a smart home, without cloud services.

Home LLM adds AI-powered voice and chat control to Home Assistant using a language model that runs entirely on the user's own hardware. It has two parts: a custom component that connects local or external language models to Home Assistant as a conversation agent, and a family of small models fine-tuned specifically for smart-home control that can run on low-power hardware such as a Raspberry Pi without a GPU.

Supported backends include the built-in llama.cpp, Ollama, a llama.cpp server for heterogeneous CPU and GPU setups, text-generation-webui, and any OpenAI- or Anthropic-compatible API. Beyond conversation, the model can also generate structured data for automations, and the integration ships with translations for English, German, French, Spanish and Polish. It requires Home Assistant 2026.5.0 or newer.

Website: https://github.com/acon96/home-llm