Memoid
Back to Tutorials
beginner 10 min

Getting Started with Memoid

Set up your first memory-enabled AI application in under 10 minutes.

Prerequisites

  • Python 3.8+ or Node.js 18+
  • A Memoid account (free tier available)
  • Basic understanding of REST APIs

In this tutorial, you’ll learn how to set up Memoid and add memory to your first AI application.

Step 1: Create an Account

First, sign up for a free Memoid account at memoid.dev/register.

Once logged in, navigate to the Dashboard and create your first project.

Step 2: Get Your API Key

In your project settings, you’ll find your API key. Copy it — you’ll need it for the next steps.

# Your API key will look something like this:
mem_sk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxx

Keep it safe! Never commit your API key to version control.

Step 3: Install the SDK

Choose your preferred language:

Python

pip install memoid

JavaScript/Node.js

npm install memoid
# or
pnpm add memoid

Go

go get github.com/memoid/memoid-go

Step 4: Initialize the Client

Create a new file and initialize the Memoid client:

Python

from memoid import MemoryClient

client = MemoryClient("your-api-key")

JavaScript

import { MemoryClient } from 'memoid';

const client = new MemoryClient('your-api-key');

Step 5: Add Your First Memory

Now let’s store a memory from a conversation:

Python

# Add a memory
result = client.add(
    messages=[
        {"role": "user", "content": "My name is Alex and I love hiking"},
        {"role": "assistant", "content": "Nice to meet you, Alex! Hiking is great exercise."}
    ],
    user_id="user_123"
)

print(f"Added {len(result.memories)} memories")
# Output: Added 2 memories
# - User's name is Alex
# - User loves hiking

JavaScript

const result = await client.add({
    messages: [
        { role: 'user', content: 'My name is Alex and I love hiking' },
        { role: 'assistant', content: 'Nice to meet you, Alex! Hiking is great exercise.' }
    ],
    userId: 'user_123'
});

console.log(`Added ${result.memories.length} memories`);

Step 6: Search Memories

Now search for relevant memories using natural language:

Python

# Search memories
results = client.search(
    query="What are the user's hobbies?",
    user_id="user_123",
    limit=5
)

for memory in results:
    print(f"- {memory.memory} (score: {memory.score:.2f})")

# Output:
# - User loves hiking (score: 0.92)

JavaScript

const results = await client.search({
    query: "What are the user's hobbies?",
    userId: 'user_123',
    limit: 5
});

results.forEach(m => {
    console.log(`- ${m.memory} (score: ${m.score.toFixed(2)})`);
});

Step 7: Use Memories in Your App

Here’s a complete example integrating memories with OpenAI:

import openai
from memoid import MemoryClient

memory = MemoryClient("your-memoid-key")
openai.api_key = "your-openai-key"

def chat_with_memory(user_id: str, message: str) -> str:
    # Get relevant memories
    memories = memory.search(query=message, user_id=user_id, limit=5)

    # Build context from memories
    context = "\n".join([f"- {m.memory}" for m in memories])

    # Generate response with context
    response = openai.chat.completions.create(
        model="gpt-4",
        messages=[
            {
                "role": "system",
                "content": f"You are a helpful assistant. Here's what you know about this user:\n{context}"
            },
            {"role": "user", "content": message}
        ]
    )

    assistant_reply = response.choices[0].message.content

    # Store the conversation
    memory.add(
        messages=[
            {"role": "user", "content": message},
            {"role": "assistant", "content": assistant_reply}
        ],
        user_id=user_id
    )

    return assistant_reply

# Try it out
response = chat_with_memory("user_123", "What outdoor activities do you think I'd enjoy?")
print(response)
# The assistant will know you love hiking and can make personalized suggestions!

Next Steps

Congratulations! You’ve added memory to your AI application. Here’s what to explore next:

Need Help?