Memori

Installation

Get Memori installed and connected to your own database in a few steps.

Want a zero-setup option? The hosted platform at app.memorilabs.ai offers 100 memories free without an API key, and 5,000/month with a free API key.

Install Memori

Install Memori
pip install memori

Install Your Database Driver

Memori works with any database that SQLAlchemy supports, plus MongoDB. Install the driver for your preferred database:

Database Drivers
# No extra install needed!
# SQLite support is included with Python.

Set Up Your Database Connection

Memori accepts a connection factory — a callable that returns a database connection. The most common approach is to use SQLAlchemy's sessionmaker.

  • Name
    conn
    Type
    callable
    Required
    Required
    Description

    A connection factory that Memori calls to get a database connection. For SQLAlchemy, this is your sessionmaker. For raw DB-API 2.0 connections, pass a function that returns a connection object.

The conn parameter is the only required configuration for open-source Memori. It tells Memori where to store all memory data.

Database Setup
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker

engine = create_engine("sqlite:///memori.db")
SessionLocal = sessionmaker(bind=engine)

# Pass SessionLocal as the connection factory
from memori import Memori
mem = Memori(conn=SessionLocal)

Create the Schema

After setting up your connection, run build() once to create the Memori tables in your database. This only needs to be done the first time, or when you upgrade Memori.

from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from memori import Memori

engine = create_engine("sqlite:///memori.db")
SessionLocal = sessionmaker(bind=engine)

mem = Memori(conn=SessionLocal)
mem.config.storage.build()  # Creates all required tables

Install Your LLM Provider

Install the SDK for your preferred LLM provider:

LLM Provider SDKs
pip install openai

Set Up Your LLM Provider Key

You will need an API key for your LLM provider:

# OpenAI
export OPENAI_API_KEY="your-openai-key"

# Anthropic
export ANTHROPIC_API_KEY="your-anthropic-key"

# Google Gemini
export GOOGLE_API_KEY="your-google-key"

Pre-download the Embedding Model

Memori uses a local embedding model for semantic search. On first run, it downloads the model automatically, which can take a moment. To pre-download it:

python -m memori setup

Verify Installation

Run a quick check to make sure everything is installed correctly:

from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from memori import Memori

engine = create_engine("sqlite:///memori.db")
SessionLocal = sessionmaker(bind=engine)

mem = Memori(conn=SessionLocal)
mem.config.storage.build()
print("Memori is ready!")

Next Steps