Memoid

Quickstart

Get up and running with Memoid in 5 minutes

This guide will help you add memory to your first AI application.

1. Create an Account

Sign up at memoid.dev/register and create a project.

2. Get Your API Key

Find your API key in the project dashboard. It looks like:

mem_sk_live_xxxxxxxxxxxxxxxxxxxx

3. Install the SDK

# Python
pip install memoid

# JavaScript
npm install memoid

# Go
go get github.com/memoid/memoid-go

4. Add a Memory

from memoid import MemoryClient

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

result = client.add(
    messages=[
        {"role": "user", "content": "I'm Alex and I love hiking"},
        {"role": "assistant", "content": "Nice to meet you, Alex!"}
    ],
    user_id="user_123"
)

print(result.memories)
# ["User's name is Alex", "User loves hiking"]

5. Search Memories

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

for memory in results:
    print(f"{memory.memory} (score: {memory.score:.2f})")
# User loves hiking (score: 0.92)

6. Use in Your App

import openai

# Get relevant context
memories = client.search(query=user_message, user_id=user_id)
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"User context:\n{context}"},
        {"role": "user", "content": user_message}
    ]
)

Next Steps