AMIRA AI Assistant for Home Assistant — Your Smart Home AI with 40+ Models

[Bobsilvio (Silvio)]

Multi-provider LLM integration with service calls, YAML editing and dashboard generation

Hi everyone

I’d like to share AI Assistant for Home Assistant, a Home Assistant add-on that provides a chat interface connected to multiple LLM providers and allows structured interaction with your HA instance.

The goal is not just “chatting with AI”, but enabling controlled, validated operations inside Home Assistant using natural language.

---

What it does

Multi-provider LLM support

You can configure and switch between multiple providers:

• Anthropic (Claude models)
• OpenAI (GPT models)
• Google (Gemini)
• NVIDIA (NIM)
• GitHub (GitHub Models)

40+ models supported depending on provider availability.

Switching model/provider only requires changing settings in the add-on configuration.

---

Native chat interface (Ingress)

• Integrated in the HA sidebar via native Ingress
• Conversation history persists across restarts
• Streaming responses (when supported by the provider)
• Visual indicators when tools/service calls are being executed
• Multilingual support (EN / IT / ES / FR)

---

Service calls & entity interaction

You can use natural language to:

• Call Home Assistant services
• Change entity states
• Query entity status
• Retrieve statistics and history

The assistant generates structured actions that are executed through HA APIs.

---

Automation & YAML generation

The assistant can:

• Generate automation YAML
• Modify existing automations
• Show diffs before applying changes
• Read and suggest edits to configuration files

Changes are not blindly applied — the workflow allows preview and validation.

---

Lovelace dashboard generation

You can request dashboard creation via natural language.

The assistant:

• Detects relevant entities
• Generates appropriate card structures
• Builds Lovelace views automatically

It validates entity existence before use to avoid empty or broken dashboards.

---

Image / Vision support

If the selected model supports vision, you can upload images or screenshots and include them in the conversation context.

---

Architecture approach

• Prompt routing depending on request type (service call, YAML edit, dashboard generation, etc.)
• Structured tool usage instead of free-form responses
• Validation steps before applying configuration changes
• Provider-agnostic design

This is not an autonomous agent — it executes user-requested actions within defined boundaries.

---

Installation

1. Add repository:
   https://github.com/Bobsilvio/ha-claude
2. Install AI Assistant for Home Assistant
3. Configure at least one API key
4. Open from the sidebar

Repository:
https://github.com/Bobsilvio/ha-claude

Issues / Support:

Bobsilvio/ha-claude

---

Why I built this

I wanted a way to interact with Home Assistant that goes beyond voice commands — something that can generate YAML, assist with configuration changes, and build dashboards while still keeping the user in control.

Feedback, edge cases and suggestions are very welcome.

[Bobsilvio (Silvio)]

Recent Updates

v3.15.2 — Confirmation Buttons & UI Polish

Features Summary

• Chat Interface: Ingress + conversation history + streaming responses
• Chat Bubble: Floating bubble on any HA page, context-aware, draggable, works without Ingress
• Confirmation Buttons: AI asks for yes/no, buttons appear automatically
• HTML Dashboards: AI can read/modify HTML dashboards keeping the same style
• Backup Management: Automatic snapshots of files with restore/delete
  
  

[Bobsilvio (Silvio)]

Ai Assistant Update – Major Enhancements Beyond v3

Now is AMIRA
A new version of AMIRA is here — expanding multi-channel communication, adding web-based AI providers, and introducing local model support.

This release significantly extends what was possible in v3.

---

What’s New

---

WhatsApp & Telegram Integration

Amira now supports messaging platforms:

WhatsApp

• Send and receive AI responses via WhatsApp
• Webhook/API-based integration
• Compatible with external providers (e.g., Twilio-style setups)

Telegram

• Full bot support
• Real-time command handling
• Two-way communication with Home Assistant

This enables true conversational AI control from your phone.

---

MCP Model Context Protocol Server

---

Ollama Support (Local AI)

You can now run Amira with local models via Ollama.

• Run fully offline
• No cloud dependency
• Choose models dynamically
• Ideal for privacy-focused or self-hosted setups

This is a major step toward full local AI control inside Home Assistant.

---

Codex Web Integration

Support for Codex via Web API is now available:

• Generate code on demand
• Use web-based authentication
• Execute structured developer prompts

Perfect for automation scripts, YAML generation, and development workflows.

---

Claude Web Mode

Direct connection to Claude via Web access:

• Token-based authentication
• No SDK dependency
• Lightweight and flexible configuration
• Faster setup compared to traditional API wrappers

This allows broader compatibility and simplified deployment.

---

Architectural Improvements

• Better logging
• Automatic provider fallback
• Cleaner configuration structure
• Improved compatibility with newer Home Assistant versions
• More modular design

---

Feature Comparison

Feature	v3	New Version
Terminal Chat
WhatsApp
Telegram
MCP Routing
Ollama Local Models
Codex Web
Claude Web

---

Why This Matters

This update transforms Amira from a single-provider assistant into a:

• Multi-channel AI system
• Hybrid cloud + local AI platform
• Messaging-integrated automation tool
• Developer-capable assistant

---

Upgrade Now

If you’re coming from v3, this release unlocks:

• Messaging control from your phone
• Local AI execution
• Web-based provider flexibility
• Smarter routing architecture

[NathanCu (Nathan Curtis)]

So
…
This makes HA-CLAUDE scalable and future-proof.???

Seems there’s some confusion as to your system name?

Also MCP == Model Context Protocol.

Please review what your LLM generates before posting.