--- title: Letta Code overview | Letta Docs description: The memory-first coding agent that lives in your terminal --- Letta Code is a deeply personalized stateful agent that lives on your local computer and can learn from experience and improve with use. Unlike Claude Code, Letta Code is [open source](https://github.com/letta-ai/letta-code), model agnostic (use Claude, GPT, Gemini, or any model you want), and most importantly, is **stateful**, meaning that you can use the same agent across many coding sessions, and have it learn and improve over time. ## Get started in 30 seconds To install Letta Code, use `npm` (requires [Node.js](https://nodejs.org/en/download) version 18+): ``` npm install -g @letta-ai/letta-code ``` Then navigate to your project and run `letta` to launch Letta Code: ``` cd your-project letta ``` On first use, you’ll be prompted to log in. Follow the instructions to authenticate Letta Code with your Letta account, then return to the terminal. 👾 **Beep boop** - you’re ready to chat! To learn how to initialize your agent’s memory and configure different LLM providers, [**continue the quickstart guide →**](/letta-code/quickstart/index.md) ## Philosophy: stateful agents Letta Code is built around long-lived agents that persist across sessions and improve with use. Rather than working in independent sessions, each session is tied to a persisted agent that learns. **Claude Code / Codex / Gemini CLI (Session-Based)**: - Sessions are independent - No learning between sessions - Context = messages in the current session + AGENTS.md - Relationship: Every conversation is like meeting a new contractor **Letta Code (Agent-Based)**: - Same agent across sessions - Persistent memory and learning over time - `/clear` and `/new` starts a new session (aka “thread” or “conversation”), but memory persists - Relationship: Like having a coworker or mentee that learns and remembers ## What can Letta Code do? **Work in your local computer**: Letta Code lives in your terminal, and can do anything you can do on your computer! Ask Letta Code to write code, edit and organize files, run programs, and more. The more Letta Code does, the more it learns. **Remember all prior interactions**: Your agent persists across sessions. It remembers your codebase, preferences, and past interactions. Memories and messages are persisted and searchable via tools, skills, and subagents. **Self-improve and evolve over time**: You can deeply customize your agent’s personality and memory system, either by directly editing its memory blocks, or by asking the agent to modify itself. Run `/init` to bootstrap project knowledge, and `/remember` to save important context. ## Learn more - [Quickstart](/letta-code/quickstart/index.md) — Set up your agent and learn the basics - [Memory](/letta-code/memory/index.md) — Understand the hierarchical memory system - [Models](/letta-code/models/index.md) — Switch models and configure toolsets - [Skills](/letta-code/skills/index.md) — Create reusable skills your agent can learn - [Subagents](/letta-code/subagents/index.md) — Delegate tasks to specialized agents - [CLI reference](/letta-code/cli-reference/index.md) — Command-line options and flags - [Headless mode](/letta-code/headless/index.md) — Run non-interactively in scripts and CI ## Additional resources - [Docker](/letta-code/docker/index.md) — Connect Letta Code to a Letta server running in Docker - [GitHub](https://github.com/letta-ai/letta-code) — Source code and issue tracker - [Discord](https://discord.gg/letta) — Discord community and support channel