---
url: https://lettuceai.app/docs/quickstart
title: "Quick Start — LettuceAI"
description: "Set up LettuceAI in under 2 minutes. Connect a provider, choose a model, and start chatting."
---

Menu 

# Quick Start

Set up LettuceAI and start chatting in under 2 minutes.

New to AI apps?

If terms like tokens, context length, provider, or model are unfamiliar, read [AI Basics](/docs/ai-basics) first.

## Step 1: Welcome & Get Started

![LettuceAI welcome screen](https://lhdgeo5fms.ufs.sh/f/m0TBUtMLsaiEGSaQBWolvZNz7b9S6JOnaWIErcYV8jTRAoKU)

When you first launch LettuceAI, you’ll see the welcome screen. From here, you can begin the guided setup or skip it and configure things later.

1.  Open LettuceAI
2.  Tap **Get Started**

Beta Build

LettuceAI is currently in beta. If you encounter issues, please report them on our GitHub repository.

## Step 2: Connect an AI Provider

![AI provider selection](https://lhdgeo5fms.ufs.sh/f/m0TBUtMLsaiERJD3yz4Jx2P34yDg6iKGIpAlcoTf9etwqHkz)

LettuceAI does not require an account. Instead, you connect your own AI providers using API keys. Keys are encrypted and stored locally on your device.

1.  Select an AI provider (for example `Chutes`)
2.  Enter your API key
3.  Optionally customize the display name or base URL
4.  Tap **Test Connection**
5.  Tap **Continue**

Need an API key?

See the [API Keys guide](/docs/api-keys) to learn where to get keys for each provider.

## Step 3: Choose Your Default Model

![Model selection screen](https://lhdgeo5fms.ufs.sh/f/m0TBUtMLsaiEStjtW5fjxYOkrVMn2NmPXpy46uELTt0boAJw)

Next, choose which model LettuceAI should use by default. You can add more models or switch between them later.

1.  Select the provider you just added
2.  Enter the exact model identifier (for example `Qwen/Qwen3-32B`)
3.  Set a friendly display name
4.  Tap **Next: Memory System**

Use the supported model

Make sure the model name matches one that is actually available from the provider you selected.

## Step 4: Configure Memory

![Memory system selection](https://lhdgeo5fms.ufs.sh/f/m0TBUtMLsaiEgoDCLuz1uLhxGKCwTQRqZ4bmt2ikFOrvslNd)

LettuceAI includes a powerful memory system designed to maintain long conversations without repeatedly sending full chat histories to the model.

-   **Dynamic Memory (Recommended):** Uses a local embedding model to retrieve relevant context and maintain long-term memory automatically.
-   **Manual Memory:** You explicitly control what gets remembered.

Recommended

Dynamic Memory provides the best balance of quality, privacy, and token cost reduction.

## Step 5: Start Chatting

![Chat screen](https://lhdgeo5fms.ufs.sh/f/m0TBUtMLsaiEzapwjd5CgsDQbf3mrGI2U5jA9RHS8i0x1naJ)

That’s it. Setup is complete. You can now start a conversation with your AI companion.

1.  Go to the **Chats** screen
2.  Create a new Character and a Persona
3.  Start Chatting!

You’re ready!

LettuceAI is now fully set up and running locally on your device.

## Where to go next

Once you are past setup, three pages are the main hubs you will return to from anywhere in the app:

-   **Onboarding**: the guided flow you just finished. It covers the welcome screen, provider setup, default model, and the memory system choice. You can re-run pieces of it later from Settings.
-   **Library**: a single view for everything you create locally. Filter tabs cover All, Characters, Personas, Lorebooks, and Images. New characters, personas, and lorebooks are created from here, including the "Generate with AI" lorebook flow.
-   **Search**: a fast finder over your characters and personas. Type to filter by name or description, then tap a result to start a chat (for characters) or open the persona editor.

Privacy First

Your API keys and chat data never leave your device. LettuceAI does not run its own servers and cannot see your conversations.

[

PreviousInstallation

](/docs/installation)[

NextAI Basics

](/docs/ai-basics)