---
name: "Build stateful agents with long-term memory using Letta"
slug: "build-stateful-agents-with-long-term-memory-using-letta"
description: "Use Letta to create agents whose identity, tools, memory blocks, and conversation state persist across sessions for long-running assistant or application workflows."
github_stars: 22658
verification: "security_reviewed"
source: "https://github.com/letta-ai/letta"
author: "Letta AI"
publisher_type: "open_source"
category: "Developer Tools"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "letta-ai/letta"
  github_stars: 22658
  npm_package: "letta"
  npm_weekly_downloads: 0
---

# Build stateful agents with long-term memory using Letta

Use Letta to create agents whose identity, tools, memory blocks, and conversation state persist across sessions for long-running assistant or application workflows.

## Prerequisites

Node.js 18+ for Letta Code or API credentials/SDKs for application integration; selected model provider

## Installation

Use the upstream install or setup path that matches your environment:
- npm install @letta-ai/letta-client
- pip install letta-client

Requirements and caveats from upstream:
- Requires [Node.js 18+](https://nodejs.org/en/download)
- Letta has a full-featured agents API, and a Python and Typescript SDK (view our [API reference](https://docs.letta.com/api)).
- TypeScript / Node.js:

Basic usage or getting-started notes:
- [Letta Code](https://docs.letta.com/letta-code): run agents locally in your terminal
- Run letta in your terminal to launch an agent with memory running on your local computer
- bash

- Source: https://github.com/letta-ai/letta
- Extracted from upstream docs: https://raw.githubusercontent.com/letta-ai/letta/HEAD/README.md

## Documentation

- https://docs.letta.com/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/build-stateful-agents-with-long-term-memory-using-letta/)