Quick Start¶

Get Memori running in 3 minutes.

1. Install¶

pip install memorisdk openai

2. Set API Key¶

export OPENAI_API_KEY="sk-your-openai-key-here"

3. Basic Usage¶

Create demo.py:

from memori import Memori
from openai import OpenAI

# Initialize OpenAI client
openai_client = OpenAI()

# Initialize memory
memori = Memori(conscious_ingest=True)
memori.enable()

# First conversation - establish context
response1 = openai_client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{
        "role": "user", 
        "content": "I'm working on a Python FastAPI project"
    }]
)
print("Assistant:", response1.choices[0].message.content)

# Second conversation - memory provides context  
response2 = openai_client.chat.completions.create(
    model="gpt-4o-mini", 
    messages=[{
        "role": "user",
        "content": "Help me add user authentication"
    }]
)
print("Assistant:", response2.choices[0].message.content)

4. Run¶

python demo.py

5. See Results¶

First response: General FastAPI help
Second response: Contextual authentication help (knows about your FastAPI project!)
Database created: memori.db with your conversation memories

What Happened?¶

Universal Recording: memori.enable() automatically captures ALL LLM conversations
Intelligent Processing: Extracts entities (Python, FastAPI, projects) and categorizes memories
Context Injection: Second conversation automatically includes relevant memories
Persistent Storage: All memories stored in SQLite database for future sessions

Pro Tip

Try asking the same questions in a new session - Memori will remember your project context!