letta-ai/letta

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

What it solves

Letta provides a framework for building stateful agents that possess long-term memory, allowing them to learn and improve their performance over time rather than being limited by a fixed context window.

How it works

It implements a system where agents have a persistent memory state that can be updated and managed. The project provides a variety of interfaces for interacting with these agents, including a terminal UI, an App Server for self-hosting, a desktop application, and a web-based chat interface. It also offers an SDK for integrating agents into TypeScript applications and supports integration with messaging channels like Slack, Telegram, and Discord.

Who it’s for

Developers building AI agents that require persistent identity, long-term memory, and the ability to evolve through interaction.

Highlights

  • own own agents via a local App Server or Letta Cloud
  • Integration with Slack, Telegram, and Discord
  • TypeScript SDK for application integration
  • Multiple interaction interfaces including terminal, desktop, and web apps

Related

  • Project
    letta-ai/letta-code

    A stateful agent harness that enables AI agents to have long-term memory, identity, and the ability to self-evolve by rewriting their own memory and skills.

  • Project
    sopaco/cortex-mem

    A Rust-based long-term memory framework for AI agents that uses a three-tier hierarchical architecture and a virtual filesystem to provide persistent, context-aware interactions.

  • Project
    framerslab/agentos

    A TypeScript AI agent framework featuring persistent cognitive memory, runtime tool forging, and personality-driven orchestration across 11 LLM providers.

  • Project
    caura-ai/caura

    Caura is an open-source governed memory layer for AI agent fleets that enables shared, self-improving knowledge storage and retrieval across multiple agents.

  • Project
    fuyuxiang/echo-agent

    A self-hosted, long-running AI agent featuring a four-layer cognitive memory system and a self-evolution engine to improve skills over time.