> This page is for NeMo Fabric, version dev.
> For other versions, use one of these documentation indexes:
> - Latest (v0.7.0) (default): https://docs.nvidia.com/nemo/fabric/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/fabric/dev/llms.txt
> - v0.7.0: https://docs.nvidia.com/nemo/fabric/v0.7.0/llms.txt
> - v0.6.1: https://docs.nvidia.com/nemo/fabric/v0.6.1/llms.txt
> - v0.6.0: https://docs.nvidia.com/nemo/fabric/v0.6.0/llms.txt
> - v0.5.0: https://docs.nvidia.com/nemo/fabric/v0.5.0/llms.txt
> - v0.4.0: https://docs.nvidia.com/nemo/fabric/v0.4.0/llms.txt
> - v0.3.0: https://docs.nvidia.com/nemo/fabric/v0.3.0/llms.txt
> - v0.2.0: https://docs.nvidia.com/nemo/fabric/v0.2.0/llms.txt
> - v0.1.1: https://docs.nvidia.com/nemo/fabric/v0.1.1/llms.txt
> - v0.1.0: https://docs.nvidia.com/nemo/fabric/v0.1.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/fabric/llms.txt.

# Start Here: Run Your First Agent

> Review a small Python function in the starter notebook or the three-part Python Quickstart.

Run your first code review with NVIDIA NeMo Fabric. Give an agent a small Python function, inspect the bug it finds, and read the result returned through NeMo Fabric. Choose the starter notebook for an interactive walkthrough or the Python Quickstart for a script you can extend.

#### [Open the Starter Notebook](#use-the-starter-notebook)

Follow the existing code-review example in Jupyter, with configuration, execution, and results explained cell by cell.

#### [Follow the Python Quickstart](#follow-the-python-quickstart)

Install one harness and run the same review task from a Python script. Then switch harnesses and add capabilities.

## Use the Starter Notebook

#### Prepare Your Checkout

The starter notebook uses Hermes Agent from a NeMo Fabric source checkout. Complete [Development Setup](/nemo/fabric/dev/contributing/setup) and the supported [Hermes Agent installation](/nemo/fabric/dev/getting-started/installation/hermes), then provide an [NVIDIA API key](https://build.nvidia.com/). The [notebook setup guide](https://github.com/NVIDIA/NeMo-Fabric/blob/main/examples/notebooks/README.md#prerequisites) explains the notebook's environment and credential prompts.

Open or download [the starter notebook on GitHub](https://github.com/NVIDIA/NeMo-Fabric/blob/main/examples/notebooks/01_quickstart.ipynb). A source checkout includes it at `examples/notebooks/01_quickstart.ipynb`.

#### Open the Notebook in Jupyter

From the prepared repository root, run:

```bash
just notebooks
```

Open `01_quickstart.ipynb` and run its cells in order. The notebook constructs the reviewer and supplies this function directly in the request; it does not need to read project files:

```python
def average(values):
    return sum(values) / len(values)
```

#### Recognize a Successful Review

With the notebook's prerequisites available, the run should return status `succeeded`. The review should identify that an empty input list causes division by zero. Wording and suggested fixes can vary; check both the status and the finding. A skipped live cell means a prerequisite is missing, not that a review completed.

The remaining cells demonstrate runtime reuse and optional diagnostics. Notebook [02_variations.ipynb](https://github.com/NVIDIA/NeMo-Fabric/blob/main/examples/notebooks/02_variations.ipynb) explores harness and configuration changes after the first run.

## Follow the Python Quickstart

These three connected guides use the same code-review task. Follow them in order; the later guides reuse the configuration from the first. An optional fourth guide moves to the source-checkout OpenShell example:

1. [Install One Harness](/nemo/fabric/dev/getting-started/quickstart). Install NeMo Fabric with LangChain Deep Agents, provide model access, and review the function. Keep the resulting `first_agent.py` for the next two guides.
2. [Switch Harnesses](/nemo/fabric/dev/getting-started/quickstart/switch-harnesses). Reuse that configuration to run Deep Agents and Hermes Agent variants, then compare results through the same application interface.
3. [Add Skills and MCP](/nemo/fabric/dev/getting-started/quickstart/skills-and-mcp). Extend the Hermes variant with a review skill and a working local MCP tool, then inspect evidence of its tool calls.
4. [Run in OpenShell (Optional)](/nemo/fabric/dev/getting-started/quickstart/openshell). On a Linux host, run the source-checkout Hermes code-review example in a sandbox.

Start with Python 3.11 or later and an [NVIDIA API key](https://build.nvidia.com/). The second guide adds a separate Python 3.14 environment for Hermes Agent; the third supplies a complete local stdio MCP server. The optional sandbox guide requires a Linux host and a source checkout. Each guide explains its additional setup. For supported platforms and other installation routes, see the [Installation Overview](/nemo/fabric/dev/getting-started/install).