acon96/home-llm
Public
Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

Home LLM

Control your Home Assistant smart home with a completely local Large Language Model. No cloud services and no subscriptions needed. Just privacy-focused AI running entirely on your own hardware.

Open your Home Assistant instance and open a repository inside the Home Assistant Community Store.

What is Home LLM?

Home LLM is a complete solution for adding AI-powered voice and chat control to Home Assistant. It consists of two parts:

  1. Local LLM Integration – A Home Assistant custom component that connects local language models to your smart home
  2. Home Models – Small, efficient AI models fine-tuned specifically for smart home control

Key Features

  • 🏠 Fully Local – Everything runs on your hardware. Your data never leaves your control (unless you want to!)
  • 🗣️ Voice & Chat Control – Use as a conversation agent with voice assistants or chat interfaces
  • 🤖 AI Task Automation – Generate dynamic content and structured data for automations
  • 🌍 Multi-Language Support – Built-in support for English, German, French, Spanish, and Polish (better translations are welcome!)
  • ⚡ Runs on Low-Power Devices – Models work on Raspberry Pi and other modest hardware -- no GPU required!
  • 🔌 Flexible Backends – Run models locally as part of Home Assistant or connect to external model providers

Quick Start

See the Setup Guide for detailed installation instructions.

Requirements: Home Assistant 2026.5.0 or newer

Local LLM Integration

The integration connects language models to Home Assistant, enabling them to understand your requests and control your smart devices.

Supported Backends

Choose how and where you want to run your models:

BackendBest For
Llama.cpp (built-in)Running models directly in Home Assistant
OllamaEasy setup on a separate GPU machine
Generic OpenAI APILM Studio, LocalAI, vLLM, and other OpenAI-compatible servers
llama.cpp serverHeterogeneous (non-uniform) GPU compute setups, including CPU + GPU inference
OpenAI 'Responses' Style APICloud services supporting the 'responses' style API
Anthropic 'Messages' Style APICloud services supporting the 'messages' style API
text-generation-webuiAdvanced users with existing setups

NOTE: When utilizing external APIs or model providers, your data will be transmitted over the internet and shared with the respective service providers. Ensure you understand the privacy implications of using these third-party services, since they will be able to see the status of all exposed entities in your Home Assistant instance, which can potentially include your current location.

Supported Device Types

The integration can control: lights, switches, fans, covers, locks, climate, media players, vacuums, buttons, timers, todo lists, and scripts

Using the Integration

As a Conversation Agent:

  • Chat with your assistant through the Home Assistant UI
  • Connect to voice pipelines with Speech-to-Text and Text-to-Speech
  • Supports voice streaming for faster responses

As an AI Task Handler:

  • Create automations that use AI to process data and generate structured responses
  • Perfect for dynamic content generation, data extraction, and intelligent decision making
  • See AI Tasks documentation for examples

Home LLM Models

The "Home" models are small language models (under 5B parameters) fine-tuned specifically for smart home control. They understand natural language commands and translate them into Home Assistant service calls.

Latest Models

Model FamilySizeLink
Llama 3.23Bacon96/Home-Llama-3.2-3B
Gemma270Macon96/Home-FunctionGemma-270m
Previous Model Versions

Stable Models:

Multilingual Experiments:

Note: Models v1 (3B) and earlier are only compatible with integration version 0.2.17 and older.

Using Other Models

Don't have dedicated hardware? You can use any instruction-tuned model with in-context learning (ICL). The integration provides examples that teach general-purpose models (like Qwen3, Llama 3, Mistral) how to control your smart home. See the Setup Guide for configuration details.

Training Your Own

The fine-tuning dataset and training scripts are included in this repository:

Documentation

Version History

VersionHighlights
v0.4.12More fixes for Home Assistant 2026.9.0 and newer, including a fix for the "Use server sampling defaults" option not being applied properly on the llama.cpp backend
v0.4.11Compatibility fix for Home Assistant 2026.9.0 and newer
v0.4.10Bug fixes and manual parsing improvements for tool calls and thinking blocks
v0.4.9Relax dependency requirements to avoid conflicting with internal HA lib versions
v0.4.8OpenAI backends rewritten using the official openai Python library for better reliability and compatibility. New "Use server sampling defaults" to let your backend set the sampling parameters. More robust tool call parsing with auto-repair for malformed JSON, ability to disable streaming for all backends.
v0.4.7Bug fixes, update default llama_cpp_python version to support new models, and support python 3.14 for new Home Assistant versions
v0.4.6Anthropic API support, on-disk caching for Llama.cpp, new tool calling dataset
v0.4.5AI Task entities, multiple LLM APIs at once, official Ollama package
v0.4Tool calling rewrite, voice streaming, agentic tool use loop, multiple configs per backend
v0.3Home Assistant LLM API support, improved prompting, HuggingFace GGUF auto-detection
Full Version History
VersionDescription
v0.4.12More fixes for Home Assistant 2026.9.0 and newer, including a fix for the "Use server sampling defaults" option not being applied properly on the llama.cpp backend
v0.4.11Compatibility fix for Home Assistant 2026.9.0 and newer
v0.4.10Bug fixes and manual parsing improvements for tool calls and thinking blocks
v0.4.9Relax dependency requirements to avoid conflicting with internal HA lib versions
v0.4.8OpenAI backends rewritten using the official openai Python library for better reliability and compatibility. New "Use server sampling defaults" to let your backend set the sampling parameters. More robust tool call parsing with auto-repair for malformed JSON, ability to disable streaming for all backends.
v0.4.7Bug fixes, update default llama_cpp_python version to support new models, and support python 3.14 for new Home Assistant versions
v0.4.6New dataset supporting proper tool calling, Add Anthropic "messages" style API support, Add on-disk caching for Llama.cpp backend
v0.4.5Add support for AI Task entities, Replace custom Ollama API implementation with the official ollama-python package, Support multiple LLM APIs at once
v0.4.4Fix issue with OpenAI backends appending /v1 to all URLs
v0.4.3Fix model config creation during setup
v0.4.2Fix default model settings, numeric config fields, finish_reason handling
v0.4.1Fix Llama.cpp models downloaded from HuggingFace
v0.4Rewrite for tool calling models, agentic tool use loop, voice streaming, multiple config sub-entries
v0.3.11Bug-fixes and llama.cpp version update
v0.3.10OpenAI "Responses" API support, HA 2025.7.0 compatibility
v0.3.9Fix conversation history
v0.3.8Thinking model support, HA 2025.4 compatibility
v0.3.7German ICL examples, multi-turn fixes
v0.3.6Small llama.cpp backend fixes
v0.3.5Polish ICL examples
v0.3.4Full Polish translation, improved language support
v0.3.3Generic OpenAI improvements, area handling
v0.3.2Script entity fixes
v0.3.1Basic area support in prompting
v0.3Home Assistant LLM API support, improved prompting
v0.2.xOllama support, in-context learning, flash attention, prompt caching
v0.1Initial Release

关于 About

A Home Assistant integration & Model to control your smart home using a Local LLM
homeassistant-custom-componentlarge-language-model

语言 Languages

Python95.2%
Jinja3.7%
Shell1.0%
Go Template0.1%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
181
Total Commits
峰值: 22次/周
Less
More

核心贡献者 Contributors