Long-Term Memory

Introduction

GLLM Memory is a flexible and extensible memory system for AI Agents with Mem0 Platform integration. It's designed to provide a robust foundation for building AI applications that can remember and retrieve information.

Installation

Prerequisites

Before installing, make sure you have:

1. Python 3.11+

2. Pip or Poetry

3. Mem0 Platform Credentials

   1. API Key — after logging in to the Mem0 console, you can create an API key from the menu on the left.

4. gcloud CLI — required because gllm-memory is a private library hosted in a private Google Cloud repository.

After installing, please run

gcloud auth login

to authorize gcloud to access the Cloud Platform with Google user credentials.

Our internal gllm-memory package is hosted in a secure Google Cloud Artifact Registry. You need to authenticate via gcloud CLI to access and download the package during installation.

Install with pip

Run the following command to install

pip install --extra-index-url "https://oauth2accesstoken:$(gcloud auth print-access-token)@glsdk.gdplabs.id/gen-ai-internal/simple/" "gllm-memory"

Install with poetry

Environment Setup

Set a Mem0 platform API key as an environment variable.

Get a Mem0 API key from Mem0 console.

Linux, macOS, or Windows WSL

export MEM0_API_KEY="m0-..."

Windows Powershell

Windows Command Prompt

Core Methods

Init Memory — Start the memory client. Use this first.

Add Memory — Save a new memory item for a user or agent.

Search Memory — Find and return the most relevant memories for a query.

List Memory — Get memories based on the provided parameters.

Delete Memory — Deletes multiple memories based on the provided parameters.

Delete Memory by User Query — Remove memories that match a query.