Quickstart

Any agents you create in Letta Code are viewable and fully interactable in the Agent Development Environment.

Setting up your agent

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:

Initializing Letta Code's memory

> /init

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

Ask Letta Code to update its memory

> /remember [optional instructions on what to remember]

Connecting to an existing Letta agent

To connect to an existing agent, use the --agent flag:

Connect to an existing agent

letta --agent [existing-agent-id]

If the agent wasn’t created inside of Letta Code, it won’t have access to coding tools (which allow it to connect to your computer) by default. Use the /link command to add the coding toolset:

Connect a non-coding agent to local coding tools

> /link

Running Letta Code in headless mode

You can also run Letta Code in headless mode, which allows you to compose your agents as UNIX programs.

Running Letta Code in headless mode

letta -p "Look around this repo and write a README.md documenting it at the root level"

Next steps

Read more about Letta Code’s rich feature set:

• Skills - Create reusable modules to extend your agent
• Memory - Understand the hierarchical memory system
• Headless mode - Run Letta Code non-interactively
• Commands reference - All CLI and interactive commands