--- title: "Home Agent" description: "Home Agent is a Marketplace integration for Home Assistant. It has 172 installs sharing analytics, needs the vendor's cloud and was last updated May 11, 2026." canonical: "https://vulpo.app/integrations/marketplace/aradlein-hass-agent-llm" url: "https://vulpo.app/integrations/marketplace/aradlein-hass-agent-llm.md" last-updated: "2026-10-22" version: "1.4" --- # Home Agent > Home Agent is a Marketplace integration for Home Assistant. It has 172 installs sharing analytics, needs the vendor's cloud and was last updated May 11, 2026. Home Agent is a conversation integration that connects Home Assistant to OpenAI-compatible language models. It works with cloud services or local servers such as Ollama, LocalAI and LM Studio, and is set up in the UI. Entity context can be passed to the model either from a fixed list of entities or by retrieving relevant ones from a ChromaDB vector database. Built-in tools let the model control and query Home Assistant, and an optional second external model can be offered for complex analysis. Conversation history can persist across restarts, and voice sessions can carry over between requests from the same device. A memory system extracts facts and preferences after conversations, with limits on stored memories and a minimum importance score. Actions are available to reindex entities and to clear a conversation. Automatic summary of the README and code of aradlein/hass-agent-llm. Something wrong, or are you the maintainer and want your own text here? [Get in touch](https://vulpo.app/contact) [Open in My Home Assistant](https://my.home-assistant.io/redirect/hacs_repository/?owner=aradlein&repository=hass-agent-llm&category=integration) On Home Assistant 2026.11 or newer? [Open it in the Marketplace](https://my.home-assistant.io/redirect/marketplace_repository/?owner=aradlein&repository=hass-agent-llm&category=integration) ## Supports - **Uses the vendor's cloud**: Needs an internet connection and an account with the vendor. - **From the Marketplace**: Installed through the Marketplace, formerly HACS. - **Actively maintained**: Its author released or pushed a change in the last six months. ## Setting it up Install it from the Marketplace and restart Home Assistant, then add it under Settings, Devices and services. ### Set up Home Agent - **Integration Name**: A friendly name for this Home Agent instance - **LLM API Base URL**: OpenAI-compatible API endpoint (e.g., api.openai.com/v1 or localhost:11434/v1 for Ollama) - **API Key**: API key for authentication (leave empty if not required) - **Model Name**: The model to use (e.g., gpt-4o-mini, llama3.1, etc.) - **Temperature**: Controls randomness (0.0-2.0). Lower is more focused, higher is more creative. - **Max Tokens**: Maximum tokens per response - **Keep Alive**: How long Ollama keeps model in memory (e.g., 5m, 24h). Use -1 for indefinite. - **Proxy Headers**: Optional custom HTTP headers as JSON, e.g. X-Ollama-Backend: llama-cpp ### Context Injection - **Context Mode**: Choose how to inject entity context: Direct (always include specified entities) or Vector DB (dynamically retrieve relevant entities) - **Context Format**: Format for entity data: JSON (structured) or Natural Language (human-readable) - **Entities to Include**: Comma-separated list of entity IDs or patterns (e.g., sensor.temperature, light.\*, climate.thermostat) ### Vector Database Configuration - **ChromaDB Host**: ChromaDB server hostname or IP address - **ChromaDB Port**: ChromaDB server port - **Collection Name**: Name of the collection containing entity embeddings - **Embedding Provider**: Choose between OpenAI or Ollama for generating embeddings - **Embedding API Base URL**: Base URL for embedding API (e.g., localhost:11434 for Ollama) - **Embedding Model**: Model name (e.g., text-embedding-3-small for OpenAI, mxbai-embed-large for Ollama) - **OpenAI API Key**: Your OpenAI API key (only required if using OpenAI provider) - **Top K Results**: Number of most relevant entities to retrieve - **Similarity Threshold**: Maximum L2 distance threshold (lower = stricter matching, typical range: 150-300) ### Conversation History - **Enable Conversation History**: Include previous conversation turns in LLM context - **Max Messages**: Maximum number of conversation turns to retain (0 for unlimited) - **Max Tokens**: Token-based limit for history (0 for unlimited) - **Persist Across Restarts**: Save conversation history across Home Assistant restarts ### System Prompt - **Use Default System Prompt**: Use Home Agent's built-in system prompt that explains tool usage and guidelines - **Custom Prompt Additions**: Additional instructions to append to the system prompt (e.g., preferences, house rules) ### Tool Configuration - **Enable Native Tools**: Enable ha\_control and ha\_query tools for Home Assistant integration - **Max Tool Calls Per Turn**: Maximum number of tool executions per conversation turn - **Tool Timeout (seconds)**: Maximum execution time for each tool call ### External LLM Tool (Optional) - **Enable External LLM Tool**: Expose query\_external\_llm tool to primary LLM for complex analysis and detailed explanations - **External LLM Base URL**: OpenAI-compatible API endpoint for external LLM - **External LLM API Key**: API key for external LLM authentication - **External LLM Model**: External model name (e.g., gpt-4o, claude-3-opus) - **External LLM Temperature**: Temperature for external LLM responses - **External LLM Max Tokens**: Maximum tokens for external LLM responses - **Auto-include Context**: Automatically pass conversation history and entity context to external LLM ### Advanced Settings - **Enable Debug Logging**: Enable detailed logging for troubleshooting - **Emit Events**: Fire Home Assistant events for conversation tracking and automation triggers ### After setup - **LLM Base URL**: OpenAI-compatible API endpoint (e.g., api.openai.com/v1 or localhost:11434/v1 for Ollama) - **API Key**: API key for authentication - **Model Name**: Model to use (e.g., gpt-4o-mini, llama3.1) - **Temperature**: Controls randomness (0.0-2.0). Lower is more focused, higher is more creative. - **Max Tokens**: Maximum tokens per response - **Keep Alive**: How long Ollama keeps model in memory (e.g., 5m, 24h). Use -1 for indefinite. - **Proxy Headers**: Optional custom HTTP headers as JSON, e.g. X-Ollama-Backend: llama-cpp - **Enable Thinking Mode**: Allow reasoning models to use extended thinking. Disable to automatically append /no\_think to prompts for faster responses. - **Context Mode**: Choose how to inject entity context - **Context Format**: Format for entity data (JSON, Natural Language, or Hybrid) - **Entities to Include**: Comma-separated list of entity IDs (e.g., sensor.temperature,light.\*) - **Max Context Tokens**: Maximum total tokens for context (entities + history + prompt). Increase if you have a model with large context window. Default: 8000. - **ChromaDB Host**: ChromaDB server hostname or IP address - **ChromaDB Port**: ChromaDB server port - **Collection Name**: Name of the collection containing entity embeddings - **Embedding Provider**: Choose between OpenAI or Ollama for generating embeddings - **Embedding API Base URL**: Base URL for embedding API (e.g., localhost:11434 for Ollama) - **Embedding Model**: Model name (e.g., text-embedding-3-small for OpenAI, mxbai-embed-large for Ollama) - **OpenAI API Key**: Your OpenAI API key (only required if using OpenAI provider) - **Top K Results**: Number of most relevant entities to retrieve - **Similarity Threshold**: Maximum L2 distance threshold (lower = stricter matching, typical range: 150-300) - **Enable Conversation History**: Include previous conversation turns in LLM context - **Max Messages**: Maximum number of conversation turns to retain - **Max Tokens**: Token-based limit for history - **Enable Voice Session Persistence**: Maintain conversation context across multiple voice interactions from the same device. When disabled, each voice request starts a fresh conversation. - **Session Timeout (minutes)**: Time in minutes before voice sessions expire and start fresh (1-120 minutes) - **Use Default System Prompt**: Use Home Agent's built-in system prompt - **Include Entity/Device Labels**: Include entity and device labels in the system prompt for better context - **Custom Prompt Additions**: Additional instructions to append to the system prompt - **Max Tool Calls Per Turn**: Maximum number of tool executions per conversation turn - **Tool Timeout (seconds)**: Maximum execution time for each tool call - **Enable External LLM Tool**: Expose query\_external\_llm tool to primary LLM - **External LLM Base URL**: OpenAI-compatible API endpoint for external LLM - **External LLM API Key**: API key for external LLM authentication - **External LLM Model**: External model name - **External LLM Temperature**: Temperature for external LLM responses - **External LLM Max Tokens**: Maximum tokens for external LLM responses - **Tool Description**: Description of when to use the external LLM - **Auto-include Context**: Automatically pass context to external LLM - **Enable Memory System**: Privacy toggle - enable or disable the entire memory system - **Enable Automatic Memory Extraction**: Automatically extract memories after each conversation - **LLM for Memory Extraction**: Choose which LLM to use for extracting memories (external is more accurate but requires External LLM to be enabled) - **Maximum Stored Memories**: Maximum number of memories to store (oldest/least important are removed when limit is reached) - **Minimum Importance (0.0-1.0)**: Filter memories by LLM-assigned importance score. Lower values (0.2-0.3) keep most memories including casual mentions. Medium values (0.4-0.5) filter out minor details. Higher values (0.6-0.8) only keep significant preferences and facts. Default 0.4 provides balanced filtering. - **Minimum Words**: Minimum number of meaningful words (\>2 characters) required for a memory to be stored. Helps filter out short, low-value memories. - **Memories to Inject in Context**: How many relevant memories to include in each conversation - **ChromaDB Collection Name**: Name of the ChromaDB collection for memory indexing Texts from the code of [aradlein/hass-agent-llm](https://github.com/aradlein/hass-agent-llm). ## Actions - **Reindex entities**: Force a full reindex of all Home Assistant entities into the vector database. - **Index entity**: Index a specific entity into the vector database. Fields: Entity ID - **Clear conversation**: Clear conversation session and start fresh with no previous context. Allows users to reset voice conversations for a specific user or device, or all conversations at once. ## From the README > A highly customizable Home Assistant custom component that provides intelligent conversational AI capabilities with advanced tool calling, context injection, and conversation history management. > > - LLM Integration - Works with OpenAI, Azure OpenAI, Ollama, LocalAI, LM Studio, or any OpenAI-compatible endpoint > - Entity Context - Automatically provides relevant entity states to the LLM > - Conversation History - Maintains context across multiple interactions with persistent storage > - Native Tools - Built-in ha\_control and ha\_query tools for home automation > - Custom Tools - Define REST API and Home Assistant service tools in configuration > - Event System - Rich events for automation triggers and monitoring > - Streaming Responses - Low-latency streaming for voice assistant integration (~10x faster) From the README of [aradlein/hass-agent-llm](https://github.com/aradlein/hass-agent-llm#readme), [MIT License](https://spdx.org/licenses/MIT.html). Shortened. ## At a glance - Kind: Marketplace integration - Category: [AI and voice](https://vulpo.app/integrations/category/ai-and-voice.md), AI models - Number: 172 installs sharing analytics; 48 GitHub stars - Connection: Needs the vendor's cloud - Upkeep: Updated in the last 6 months - Needs: Needs the Marketplace (HACS on 2026.10 and older) - Latest version: v0.9.5, last updated May 11, 2026 - Domain: `home_agent` - Source: - Issues: Independent directory, made by the developer of Vulpo. Not affiliated with Home Assistant or the Open Home Foundation. [About these numbers](https://vulpo.app/integrations/about) Last updated 2026-10-22. Source: https://vulpo.app/integrations/marketplace/aradlein-hass-agent-llm --- - HTML version of this page: https://vulpo.app/integrations/marketplace/aradlein-hass-agent-llm - Site index for agents: https://vulpo.app/llms.txt - Everything in one document: https://vulpo.app/llms-full.txt - All pages: https://vulpo.app/sitemap.xml