Letta (MemGPT)
Framework for building LLM agents with persistent memory and self-editing.
About
Letta, formerly MemGPT, is a framework for building stateful LLM agents with persistent memory that grows and self-edits over time, letting agents retain context well beyond a single context window. It runs agents locally or through an agents API for integration into applications, supports skills and subagents, and is model-agnostic. The project includes a CLI and a Python interface. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Agents & Orchestration
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Python agent framework that brings Pydantic-style type safety to LLM applications.
Microsoft's framework for building multi-agent AI systems
Lightweight agent framework by Hugging Face for building tool-using AI agents.
Platform for building stateful AI agents with advanced long-term memory and self-improvement.
Memory layer for AI assistants enabling persistent personalized interactions.
Drag-and-drop UI for building LLM flows and AI agents.