Set up Letta

The Letta web app is the quickest way to get started. From one interface, you can create agents, inspect their memory, connect model providers, and choose where their tools run. You can also install it as a desktop app.

Prefer working in a terminal, or want agents stored only on your machine? Follow the Letta CLI path instead.

Path 1: Letta web app

The web app works with agents backed up to your Letta account. Where the agent’s state lives and where its tools execute are separate choices.

1. Sign in

Open chat.letta.com and sign in with your Letta account. If you don’t have one, you’ll be prompted to create a free account.

2. Connect a model provider

Agents can use Letta Auto, pay-as-you-go models, and supported providers or coding plans connected to your account. They cannot use model servers running only on your local machine.

To connect a provider, open Preferences > Models, then choose a model from the model selector.

Plans and model options change over time. See the pricing and model guide for current details.

3. Choose where tools run (optional)

The web app runs tools in a managed cloud sandbox by default. To let the agent read files or run commands on your own machine instead:

1. Install the Letta CLI on that machine and run /login.
2. Run letta server and leave it running.
3. In chat.letta.com, select the machine from the environment picker.

Permission modes and allow/deny rules determine which actions require confirmation. Review these settings before connecting a machine that contains sensitive files or credentials. See the remote environments and permissions documentation for details.

Path 2: Letta CLI

Install Node.js 22.19 or newer, then install the Letta CLI:

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

Start the Letta CLI from the directory where you want the agent to work:

cd /path/to/your/project
letta

On first launch, the Letta CLI creates a local agent without requiring a login. Use /connect to add a supported model provider, coding plan, or local inference server:

> /connect

Run /login if you want cloud backup and access to your agents from other devices. Once your model is connected, run /init to let the agent inspect the current project and bootstrap its memory:

> /init

Quick reference

Command	Action	Example
letta	Start interactive terminal mode	letta
/connect	Connect model providers, plans, or local inference	> /connect
/login	Sign in with Letta	> /login
/model	Switch the active model	> /model
/init	Bootstrap agent memory for the current project	> /init
exit	Exit the Letta CLI	> exit or Ctrl+C

Next step

Now that you’re set up and a model is connected, create an agent and verify that its memory persists across conversations.

Continue to Meet your agent.