Skip to content
forked from letta-ai/letta

Teaching LLMs memory management for unbounded context ๐Ÿ“š๐Ÿฆ™

License

Notifications You must be signed in to change notification settings

defrecord/MemGPT

ย 
ย 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

MemGPT

Overview

Part of the DEFRecord 2025 Engineering Strategy, this repository contributes to our development ecosystem.

Strategic Alignment

This project aligns with our 2025 strategy through:

  • Tool Integration
  • System Compatibility
  • Performance Standards
  • Documentation Requirements

Features

  • Core functionality
  • Integration capabilities
  • Documentation
  • Testing framework

Getting Started

Prerequisites

  • Python 3.8+
  • Git
  • Docker (optional)

Installation

  1. Clone the repository:

    git clone https://github.com/defrecord/MemGPT.git
    cd MemGPT
  2. Install dependencies:

    pip install -r requirements.txt
  3. Configure environment:

    cp .env.example .env
    # Edit .env with your settings
  4. Run tests:

    python -m pytest

Integration

This project integrates with the DEFRecord ecosystem:

  • AI Infrastructure: Compatible with AI infrastructure
  • Tool Chain: Integrates with tool chain
  • Research Framework: Supports research framework

Contributing

We welcome contributions! Please see our Contributing Guide and review our Code of Conduct.

Documentation

Community

License

This project is licensed under the terms of the MIT license. See LICENSE for more details.

About

Teaching LLMs memory management for unbounded context ๐Ÿ“š๐Ÿฆ™

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.5%
  • Other 0.5%