This repository introduces the Letta framework, empowering developers to build LLM-based agents with long-term, persistent memory and advanced reasoning capabilities. It leverages concepts from MemGPT to optimize context usage and enable multi-agent collaboration for real-world applications like research, HR, and task management.

This project is a concept demonstration of a layered memory system for Large Language Models. It includes a CLI chatbot and an AI playing Zork I with 'FROTZ' as examples. The true value lies in the memory_handle.py module, designed for easy integration into any Python project requiring LLM memory management (AI agents, games, etc.).