Letta Code

Letta Code is a memory-first coding harness, built on top of the Letta API. Instead of working in independent sessions, you work with a persisted agent that learns over time and is portable across models (Claude Sonnet/Opus 4.5, GPT-5.2-Codex, Gemini 3 Pro, GLM-4.7, and more).

Read more about how to use Letta Code on the official docs page.

Get started

Install the package via npm:

npm install -g @letta-ai/letta-code

Navigate to your project directory and run letta (see various command-line options on the docs).

Run /connect to configure your own LLM API keys (OpenAI, Anthropic, etc.), and use /model to swap models.

Note

By default, Letta Code will to connect to the Letta API. Use /connect to use your own LLM API keys and coding plans (Codex, zAI, Minimax) for free. Set LETTA_BASE_URL to connect to an external Docker server.

Philosophy

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 starts a new conversation (aka "thread" or "session"), but memory persists
• Relationship: Like having a coworker or mentee that learns and remembers

Agent Memory & Learning

If you’re using Letta Code for the first time, you will likely want to run the /init command to initialize the agent’s memory system:

> /init

Over time, the agent will update its memory as it learns. To actively guide your agents memory, you can use the /remember command:

> /remember [optional instructions on what to remember]

Letta Code works with skills (reusable modules that teach your agent new capabilities in a .skills directory), but additionally supports skill learning. You can ask your agent to learn a skill from it's current trajectory with the command:

> /skill [optional instructions on what skill to learn]

Read the docs to learn more about skills and skill learning.

Community maintained packages are available for Arch Linux users on the AUR:

yay -S letta-code # release
yay -S letta-code-git # nightly
yay -S letta-code-bin # prebuilt release

---

Made with 💜 in San Francisco