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, GPT-5, Gemini 3 Pro, GLM-4.6, and more).
Read more about how to use Letta Code on the official docs page.
Get started
Requirements:
- Node.js (version 18+)
- A Letta Developer Platform account (or a self-hosted Letta server)
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):
Memory and Skill Learning
All agents in Letta are stateful: they maintain context forever and can self-edit their own memory blocks.
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]
Skills are reusable modules that teach your agent new capabilities. They’re automatically discovered from your project’s .skills directory and loaded into the agent’s memory at session start. The easiest way to create a skill is using the interactive skill creation mode:
> /skill
Read the docs to learn more about skills and skill learning.
Made with 💜 in San Francisco