Screenshots From the README of ITSpecialist111/ai_automation_suggester.
About
AI Automation Suggester is an integration that uses language models to suggest Home Assistant automations as YAML. It looks at entities, areas, devices and existing automations, and can connect to cloud providers such as OpenAI, Anthropic, Google and Groq, or to local ones such as LocalAI and Ollama. A custom OpenAI-compatible endpoint is also supported, and each provider has its own model, temperature and token limit settings. Suggestions arrive as persistent notifications and are exposed through sensors, and a history keeps provider, model, review status and generated YAML. Actions can generate suggestions on demand, clear the history, or mark a stored suggestion as accepted, declined or dismissed. Prompts, domain filters, entity limits and randomized entity selection shape what is analyzed, and setup is done in the UI.
Automatic summary of the README and code of ITSpecialist111/ai_automation_suggester. Something wrong, or are you the maintainer and want your own text here? Get in touch
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.
Provides
- Sensors
Setting it up
Install it from the Marketplace and restart Home Assistant, then add it under Settings, Devices and services.
Select AI Provider
- AI Provider
Configure OpenAI
- OpenAI API Key
- OpenAI Model
- Temperature
- Max Input Tokens
- Max Output Tokens
Configure Anthropic
- Anthropic API Key
- Anthropic Model
- Max Input Tokens
- Max Output Tokens
Configure Google
- Google API Key
- Google Model
- Temperature
- Max Input Tokens
- Max Output Tokens
Configure Groq
- Groq API Key
- Groq Model
- Temperature
- Max Input Tokens
- Max Output Tokens
Configure LocalAI
- LocalAI IP Address
- LocalAI Port
- Use HTTPS for LocalAI
- LocalAI Model
- Temperature
- Max Input Tokens
- Max Output Tokens
Configure Ollama
- Ollama/Open WebUI Base URL
- Ollama/Open WebUI API Key (optional)
- Ollama IP Address
- Ollama Port
- Use HTTPS for Ollama
- Ollama Model
- Temperature
- Disable Think Mode (Ollama)
- Max Input Tokens
- Max Output Tokens
Configure Custom OpenAI
- Custom OpenAI Endpoint
- Custom OpenAI API Key (Optional)
- Custom OpenAI Model
- Temperature
- Max Input Tokens
- Max Output Tokens
After setup
- OpenAI API Key
- OpenAI Model
- Temperature (OpenAI)
- Anthropic API Key
- Anthropic Model
- Google API Key
- Google Model
- Temperature (Google)
- Groq API Key
- Groq Model
- Temperature (Groq)
- LocalAI IP Address
- LocalAI Port
- Use HTTPS for LocalAI
- LocalAI Model
Texts from the code of ITSpecialist111/ai_automation_suggester.
Actions
- Generate SuggestionsManually trigger AI automation suggestions.Fields: Provider Configuration, Custom Prompt, Consider All Entities, Domains, Entity Limit, Read 'automations.yaml' file, Automation Limit, Read 'scripts.yaml' file, Script Limit, Exclude Domains
- Clear Suggestion HistoryClear all stored AI automation suggestions.
- Update SuggestionUpdate the review status for a stored AI automation suggestion.Fields: Suggestion ID, Status
From the README
An AI‑powered assistant for Home Assistant that leverages large language models to understand your unique smart home environment – your entities, areas, devices, and existing automations. It proposes intelligent, actionable YAML suggestions tailored to your specific setup, helping you unlock your home's full potential.
- Multi-Provider Support: Connect to OpenAI, OpenAI Azure, Anthropic, Google, Groq, LocalAI, Ollama, Mistral, Perplexity, OpenRouter, Requesty, MiniMax, or LiteLLM (100+ backends) with full…
- Temperature control for all providers (0.0 - 2.0)
- Model selection with provider-specific defaults
- Secure API key storage
- Custom endpoints for compatible providers
- Ollama's Disable Think option sends native think: false and the legacy /no_think prompt hint. Leaving it off preserves the model's default thinking behavior.
- Customizable Prompts and Filters: Tailor suggestions using system prompts, domain filters, and entity limits.
- Persistent Suggestion History: Retain recent suggestions with provider/model metadata, review status, warnings, and generated YAML.
- Review Actions: Mark stored suggestions as accepted, declined, or dismissed through services or the bundled dashboard card.
- Randomized Entity Selection: Prevent repetitive suggestions and discover new opportunities.
- Context-Rich Insights: Incorporates device and area information for smarter, more relevant ideas.
- Persistent Notifications: Receive suggestions directly in your Home Assistant interface.
Shows in Vulpo
Chart card, Apple Watch.Information
- Installs
- 2.1k sharing analytics
- GitHub stars
- 805
- Connection
- Uses the vendor's cloud
- Upkeep
- Updated in the last 6 months
- Version
- v1.7.0,
- Category
- AI and voice, AI models
- Kind
- Marketplace integration
- Needs
- Needs the Marketplace (HACS on 2026.10 and older)
- Domain
ai_automation_suggester- Issues
- Report an issue













