Skip to content

🏡 AI Smart Home

Smart Home with AI: Your private AI Agent using LangGraph, LangChain, Ollama to control home appliances which are being controlled via Micro-controllers like ESP32, ESP8266 etc. It is designed to work completely offline & private in nature. Users can interact to the AI with text prompts or voice commands to control the home appliances. This is a prototype which can be improved and modified hugely

📽️ Demo

You can play below Video or click this Youtube Link to see the demo. Please let me know in the comments, how do you feel about this App.

You can buy me a coffee via this link or tap on below image. Thank you 🙏.

🖧 Our Scematic Architecture

This is the scematic flow diagram
Flow-Diagram

🧑‍💻 Quickstart Guide

Let's go step by step.

Here is the full codebase on GitHub 

git clone https://github.com/daslearning-org/AI-Home-Automation.git

🦾 Setting up the ESP8266

  1. Below is the scematic connection diagram . Connect your appliances accordingly. You can Checkout my DIY-Video to get more insight.
    ESP8266-Diagram

  2. Load the Code on ESP8266 using Arduino IDE

  3. Change the code with your WiFi SSID & Password here 
    /* Put SSID & Password of your Router*/
const char* ssid = "daslearning";
const char* password = "123456789";
  4. You need to install ArduinoJson library explicitly (Other libraries are managed automatically when we install the ESP8266 Board manager)
  5. Optionally, you can upload the data folder to static memory using any upload tool such as LittleFS-DataUpload to use the direct HTML based website to control the LEDs & bypass the AI .
  6. Finally, upload the sketch (program) from IDE & Volla, your ESP8266 is ready.

🤖 Setting up your AI platform

💻 Run Ollama Backend

  1. Install Ollama on your system from the official website

  2. Then Pull the required models 

    ollama pull llama3.2
# Check the models
ollama list

🐍 Run the Python AI App

You can check the App aiAgents to get more insights

  1. Steps to run the App 

    cd ./aiAgents/

# Install the dependencies
pip install -r requirements.txt # virtual environment is recommended

# Set the required enviroment variables (use `setx` command on windows)
export HOME_API_BASE="http://<your-esp8266-ip>" # This is needed for the AI app to connect to ESP8266
export OLLAMA_API_BASE="http://<your-ollama-ip>:<port>" # Optional: defaults to localhost:11434
export AUDIO_MODEL="<other-vosk-model>" # Optional: default to `en-in` (Indian English small)

# Run the APP
python app.py

  2. Access the App at http://localhost:7860 from the same device or http://<IP>:7860 from another device in the local network.
    Please note: the microphone access would be disabled on other devices as the app is not running on HTTPS .

✉️ Contact Information

Please visit our contact page 👉🏽 Contact Us