> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/ai-workbench/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/ai-workbench/_mcp/server.

> AI Workbench Basic Quickstart (CLI)

# Basic Quickstart (CLI)

Use this documentation to get a basic introduction to [NVIDIA AI Workbench](/ai-workbench/overview/introduction). For the full list of quickstarts, see [Quickstart Guides](/ai-workbench/quickstart/overview).

In this quickstart, you use the [AI Workbench CLI](/ai-workbench/reference/user-interface/cli) to perform the following tasks:

1. [Start AI Workbench and Open a Location](/ai-workbench/quickstart/quickstart-cli#start-ai-workbench-and-open-a-location)
2. [Create a New Project](/ai-workbench/quickstart/quickstart-cli#create-a-new-project)
3. [Use JupyterLab to Write Simple Code](/ai-workbench/quickstart/quickstart-cli#use-jupyterlab-to-write-simple-code)
4. [(Optional) Publish Your Project to a Git Server](/ai-workbench/quickstart/quickstart-cli#optional-publish-your-project-to-a-git-server)

## Prerequisites

Before you can complete the steps in this quickstart, you need the following:

- NVIDIA AI Workbench is installed on your local system.

## Start AI Workbench and Open a Location

1. Open a command shell by doing one of the following:

   - **On macOS or Ubuntu** — Open your favorite command shell, such as terminal.

   - **On Windows** — Open the WSL app by searching for WSL in your app list. When the WSL app opens, you should see a command prompt similar to the following:

     ```shell
     workbench@computer-name:~$
     ```

     <Tip>

     You can also use Terminal, Command Prompt, or Windows PowerShell, and access WSL by using the command `wsl -d NVIDIA-Workbench`.

     </Tip>

2. Check the available locations (contexts) by running the following command.

   ```shell
   nvwb list contexts
   ```

   If you haven't added any remote locations yet, the only available location is the local computer. The output should look similar to the following.

   ```shell
     NAME  | DESCRIPTION | HOSTNAME  |  STATUS
   --------|-------------|-----------|---------------
     local | My Computer | localhost | Not Running
   ```

3. Run the following command to start the local location.

   ```shell
   nvwb activate local
   ```

   AI Workbench starts and connects to your computer, and `(nvwb:local)` now appears at the beginning of your command prompt.

## Create a New Project

1. Start the process to create a project by running the following command.

   ```shell
   nvwb create project
   ```

2. Enter the project name, description, and press enter to choose the Python Basic container as the base environment for your project. You should see prompts similar to the following.

   ```shell
   ? Enter a unique name for the project: test-cli-proj
   ? Enter a description: A hello world test project
   ? Choose a base environment: Python Basic

     Created new project 'test-cli-proj' (/home/nvidia/nvidia-workbench/test-project)

     ✓ Container build complete (59.172564951s)
   ```

3. After you see **Container build complete**, use the following command to open the project.

   ```shell
   nvwb open test-cli-proj
   ```

   AI Workbench opens your project, changes to the project directory, and `(nvwb:local/test-cli-proj)` now appears at the beginning of your command prompt.

## Use JupyterLab to Write Simple Code

1. To open JupyterLab, run the following command.

   JupyterLab opens in your default browser ready for you to start working.

   ```shell
   nvwb start jupyterlab
   ```

2. In JupyterLab, do the following.

   1. Navigate to the *code* folder.
   2. Create a new notebook by choosing Python 3 (ipykernel).
   3. In the new notebook, enter `print("Hello World!")`.
   4. Click run to verify the code works correctly.
   5. Save the notebook, and name the file *hello-world.ipynb*.

<img src="/ai-workbench/_fern-img/9fbea7080db6002106f51b9ee92c9024d7bdb239ed387913e8dcc6bb049aa79e.webp" alt="" width="768" />

3. In JupyterLab, choose **File**, and then click **Shut Down**. Confirm shut down and close the browser tab.

4. In your command shell, run the following command to stop your environment.

   ```shell
   nvwb stop --container
   ```

## (Optional) Publish Your Project to a Git Server

Each AI Workbench project is stored as a Git repository.
When you are ready to save changes to your project, you commit and push the changes to your Git repository.
For more information, see [Connect to Git](/ai-workbench/how-to/integrations/github-gitlab).

1. Check for changes to your project by running the following command.

   ```shell
   nvwb status
   ```

   You should see output similar to the following. In this case, there is one new file, the notebook that you added.

   ```shell
   Name: test-cli-proj (/home/workbench/nvidia-workbench/test-cli-proj)
   Description: A hello world test project
   Environment: No Build Required
   Container: Stopped
   Applications:
     jupyterlab: Stopped
   Local Repository: 1 Added
   ```

2. To create a commit that contains your changes, run the following command.

   ```shell
   nvwb commit
   ```

   AI Workbench creates the commit message for you.

3. Press enter to accept the commit message and commit your changes.

4. To publish your changes to a Git server, run the following command. You are prompted for the information to publish your changes.

   ```shell
   nvwb publish
   ```

5. Open *https://github.com/&lt;user_name>/test-cli-proj* and verify that you see your project.

## Related Topics

- [Basic Quickstart](/ai-workbench/quickstart/quickstart-basic)
- [Walkthrough: Project Dashboard for Onboarding, Monitoring and Managing Your Project](/ai-workbench/quickstart/quickstart-dashboards)
- [Walkthrough: Customize Your Environment (CLI)](/ai-workbench/quickstart/quickstart-environment-cli)
- [Advanced Walkthrough: Hybrid RAG](/ai-workbench/quickstart/quickstart-hybrid-rag)
- Explore [NVIDIA AI Workbench Example Projects](/ai-workbench/quickstart/example-projects)
- Explore the [NVIDIA Developer Forum](https://forums.developer.nvidia.com/c/ai-data-science/nvidia-ai-workbench/671)

**Learn the Concepts**

- [AI Workbench Command Line Interface (CLI) Reference](/ai-workbench/reference/user-interface/cli)
- [How to Work with AI Workbench Projects](/ai-workbench/how-to/projects/overview)
- [Add a Brev Instance](/ai-workbench/how-to/locations/add-brev)
- [Integrations and Credentials](/ai-workbench/reference/faq#integrations-and-credentials)
- [Applications](/ai-workbench/concepts/application-concept)