Back
Mem0 Demo Agent

Mem0 Demo Agent

by Joel Samuel

Deploy w/ Agentuity
Mem0MemoryE-commerceProduct RecommendationsPythonOpenAI SDK

Mem0 Demo Agent - Best Buy Electronics Assistant

Welcome to the Mem0 Demo Agent! This intelligent assistant demonstrates the power of persistent memory in AI agents by acting as a personalized Best Buy electronics expert that remembers your preferences across conversations.

Setup:

  • You will need to create an account at their website: Mem0
  • From here you can view your Dashboard and get your API Key
  • You can also view requests you made, users you made, and memories you created

What This Agent Does

This agent is a Best Buy customer service assistant that:

  • Provides personalized product recommendations for laptops, TVs, and phones
  • Remembers your preferences using Mem0's memory capabilities
  • Considers your budget and specific use cases
  • Explains WHY each product fits your needs
  • Compares products with detailed pros and cons
  • Maintains conversation context across multiple interactions

Key Features:

  • Persistent Memory: Remembers your past conversations, preferences, and requirements
  • Product Database: Access to curated electronics with detailed specs and pricing
  • Smart Recommendations: AI-powered suggestions based on your specific needs
  • Budget-Aware: Finds options within your price range
  • Use Case Matching: Matches products to your intended use (gaming, work, student, etc.)

How Memory Works

The agent uses Mem0 to create a persistent memory layer that:

  1. Stores Conversations: Every interaction is saved for future reference
  2. Learns Preferences: Remembers your budget ranges, brand preferences, and use cases
  3. Provides Context: Uses past conversations to give better recommendations
  4. Personalizes Experience: Tailors responses based on your history

Example memory scenarios:

  • "I remember you mentioned you're a college student with a $800 budget"
  • "Based on our previous conversation about gaming, here are some updated options"
  • "You preferred laptops with good battery life last time, so I've prioritized that"

Code

  • Swap out USER_ID for your user to store information
#Creates a memory instance 
memory_client = MemoryClient() 

#Searches for memory based off of user question within the users storage (based off of the user_id)
memory_client.search(user_question, user_id=user_id)

#Store interaction in memory for future context  
new_interaction = [  
	{"role": "user", "content": user_question},  
	{"role": "assistant", "content": answer}  
]  
memory_client.add(messages=new_interaction, user_id=user_id)

Before you begin, ensure you have:

  • Python: Version 3.10 or higher
  • UV: Version 0.5.25 or higher (Documentation)
  • Mem0 API Key: For memory functionality

🚀 Getting Started

1. Authentication

Before using Agentuity, you need to authenticate:

agentuity login

This command will open a browser window where you can log in to your Agentuity account.

2. Set Up Environment Variables

Within the .env file (Has Agentuity Keys in it), add your mem0 API Key:

# Required API Keys
MEM0_API_KEY=your_mem0_api_key_here

Or set them using Agentuity:

agentuity env set --secret MEM0_API_KEY your_mem0_api_key

3. Install Dependencies

uv sync

4. Development Mode

Run your project in development mode with:

agentuity dev

This will start your project and open a new browser window connecting your Agent to the Agentuity Console in Live Mode, allowing you to test and debug your agent in real-time.

You can also start your project in development mode without connecting to the Agentuity Console:

uv run server.py

Test the agent with sample prompts like:

  • "I need a laptop for college under $800"
  • "What's the best TV for gaming?"
  • "Recommend a phone with great camera under $700"

5. Creating Additional Agents

To create a new agent in your project:

agentuity agent new

Follow the interactive prompts to configure your agent.

Available Products

The agent has knowledge of current Best Buy inventory:

💻 Laptops

  • MacBook Air M3 ($1,099) - Premium, lightweight, excellent battery
  • Dell XPS 13 ($899) - Business-focused, compact design
  • ASUS ROG Strix G15 ($1,299) - Gaming powerhouse with RTX 4060
  • HP Pavilion 15 ($549) - Budget-friendly for basic tasks

📺 TVs

  • Sony BRAVIA XR A95L OLED ($2,499) - Premium OLED with perfect blacks
  • Samsung QN90C Neo QLED ($1,799) - Bright display, great for gaming
  • LG C3 OLED ($1,499) - Excellent gaming TV with 120Hz
  • TCL 6-Series ($699) - Budget 4K with good value

📱 Phones

  • iPhone 15 Pro ($999) - Premium with excellent cameras
  • Samsung Galaxy S24 ($799) - Android flagship with AI features
  • Google Pixel 8 ($699) - Best Android cameras, clean software
  • iPhone SE ($429) - Affordable iPhone option

💬 Example Conversations

First Interaction:

User: "I need a laptop for college under $800"
Agent: "Great! For college under $800, I'd recommend the Dell XPS 13 at $899 (slightly over) or HP Pavilion 15 at $549. What's your major? Are you doing any specific tasks like coding, design, or just general coursework?"

Follow-up Conversation (with memory):

User: "What about gaming laptops?"
Agent: "I remember you mentioned you're a college student with an $800 budget. For gaming, the HP Pavilion 15 won't handle modern games well. You might want to consider stretching to the ASUS ROG Strix G15 at $1,299 - it has an RTX 4060 perfect for gaming. Would you like me to find some alternatives in your original budget range?"

🌐 Deployment

When you're ready to deploy your agent to the Agentuity Cloud:

agentuity deploy

This command will bundle your agent and deploy it to the cloud, making it accessible via the Agentuity platform.

The agent will be available via API endpoints and can be integrated into:

  • Web applications
  • Mobile apps
  • Customer service platforms
  • E-commerce sites

Project Structure

├── agentuity-agents/
│   └── mem0DemoAgent/
│       ├── __init__.py
│       └── agent.py          # Main agent with memory integration
├── .uv.lock/                    # Virtual environment (created by UV)
├── .env                      # API keys 
├── pyproject.toml           # Dependencies (agentuity, openai, mem0ai)
├── agentuity.yaml
└── server.py

🔧 Configuration

Your project configuration is stored in agentuity.yaml. This file defines your agents, development settings, and deployment configuration.

Memory Settings

The agent uses a consistent USER_ID for memory storage. You can customize this in the code or environment variables.

Product Database

Products are stored in PRODUCT_DATABASE with:

  • Detailed specifications
  • Use case categories
  • Pros and cons
  • Price information

🛠️ Advanced Usage

Environment Variables

You can set environment variables for your project:

agentuity env set KEY VALUE

Secrets Management

For sensitive information, use secrets:

agentuity env set --secret KEY VALUE

📖 Documentation

For comprehensive documentation:

🆘 Troubleshooting

If you encounter any issues:

  1. Check the Agentuity documentation
  2. Join our Discord community for support
  3. Visit Mem0 Discord for memory-specific questions
  4. Contact the Agentuity support team

📝 License

This project is licensed under the terms specified in the LICENSE file.