Skip to main content
There are three ways to build your first nao project:
  • With your coding agent (recommended): install the nao skills and let Claude Code, Codex, Cursor or any skills-compatible agent build the project for you.
  • On nao Cloud: sign up and let the onboarding agent set up your project in the browser, with nothing to install.
  • Manually with the CLI: run nao init, nao debug, nao sync and nao chat yourself.
nao ships skills that teach Claude Code, Codex, Cursor or any skills-compatible agent how to build a nao project end to end: scope the tables, write nao_config.yaml, sync, write RULES.md and create tests. Open your agent with the setup prompt in one click: Or follow the steps below.

​
1. Install the nao CLI and the nao skills

In the folder where you want your project:
nao skills is a thin wrapper around npx skills (Node.js 18+ required). npx skills add getnao/nao works too.

​
2. Ask your agent to set up nao

Open Claude Code, Codex or Cursor in that folder and paste:
The agent asks you once for your warehouse, the tables in scope, extra context (dbt repo, docs) and your LLM provider, then runs nao init, nao sync, and writes your first RULES.md.

​
3. Launch the chat

The nao chat opens at http://localhost:5005. Start asking questions. Keep using the skills afterwards to write rules, create tests, audit your context, and deploy it. See Skills.

​
Option 2: set it up on nao Cloud

nao Cloud is the hosted version of nao: nothing to install or deploy. Every new organization gets a 14-day free trial and $20 of nao credits, so you can start without an LLM API key.

​
1. Sign up

Create your account at app.getnao.io/signup with Google, GitHub, or email and password. While you set up, you can try nao on the Jaffle Shop example project.

​
2. Follow the onboarding agent

Click Set up on the Start using your data card in the sidebar. The onboarding agent asks where you are starting from and guides you:
  • Connect warehouse: enter your warehouse credentials, pick the tables to sync, optionally add business context, and nao builds the project for you in the cloud (sync and a first RULES.md).
  • Import project: deploy a nao project from your machine or import it from GitHub, or build a new one locally with your coding agent first.

​
3. Start chatting

When the project is ready, click Start chatting and ask your first question.

nao Cloud

Sign-up, the example project, every onboarding path, and inviting your team

​
Option 3: set it up manually with the CLI

​
Step 1: Install nao-core package

​
Step 2: Initialize a nao project

This command will ask you:
  • To name your project (defaults to the current folder name - press Enter to accept)
  • If you want to connect a database (optional)
  • If you want to set up an LLM (optional)
  • If you want to add a git repository to the agent context (optional)
You can skip any optional question and configure it later in your nao_config.yaml file. Slack, Notion, MCP servers, and skills are no longer prompted during nao init - add them directly in nao_config.yaml.
This will create:
  • A new folder with your project name
  • An architecture for your context files
  • A nao_config.yaml configuration file
  • A RULES.md file
  • A tests/ folder with a starter test_example.yml test file

​
Step 3: Verify your setup

cd to the project folder and run:
This command checks your configuration and displays any issues.

​
Step 4: Synchronize your context

This will populate your context folder with your context files (data, metadata, repos, etc.).

​
Step 5: Launch the chat and ask questions

You have two options to access the chat UI:

​
Using nao chat

This will start the nao chat UI. It will open the chat interface in your browser at http://localhost:5005.

​
Using Docker

Instead of nao chat, you can use Docker to run the UI: With built-in example:
With your project:
Access the UI at http://localhost:5005 and add your LLM API key in the settings. From there, you can start asking questions to your agent!

​
Step 6: Evaluate your agent

nao init scaffolds a starter test file at tests/test_example.yml. You can add more test files with questions and expected SQL in YAML format, then measure your agent’s performance:
View results in tests panel:

Evaluation Guide

Learn how to build comprehensive test suites and evaluate your agent

​
What’s Next?

Skills

Install five published skills to let your agentic CLI automate setup, rules, tests, and audits

Context Builder

Learn how to build and customize your agent’s context

Self-Hosting

Deploy your agent in production

Chat Interface

Explore the chat interface features

nao Cloud

Use our managed cloud service