NVIDIA NeMo Agent Toolkit Examples

This repository contains community examples for the NVIDIA NeMo Agent Toolkit. Whether you're new to using the toolkit, an experienced user looking for inspiration, or hoping to share your own examples with the community, this repository will help you get started.

[!NOTE]
Both the NeMo Agent Toolkit repository and this repository contain examples. However, there are some differences in the examples between the two repositories:

Repository	Example Focus	Update Cadence
NeMo Agent Toolkit	Examples focused on toolkit features and capabilities	Updated each release to work with latest version
NeMo Agent Toolkit Examples	Examples driven by community use cases and scenarios	Bound to specific toolkit versions, updated as needed

Getting Started

Each example is a self-contained directory that contains a README with instructions for running the example.

All examples require a local clone of this repository, uv, and a Python 3.11+ environment. Please follow the instructions below to get started.

1. Clone the repository

   git clone https://github.com/NVIDIA/NeMo-Agent-Toolkit-Examples.git
   cd NeMo-Agent-Toolkit-Examples

2. Fetch the data sets by downloading the LFS files.

   git lfs install
   git lfs fetch
   git lfs pull

3. Install uv using the instructions here.

4. Create a new environment using the following command:

   uv venv --python 3.13 --seed .venv
   source .venv/bin/activate
   
   uv sync --dev

   [!NOTE]
   Python 3.11 & 3.12 are also supported simply replace 3.13 with 3.11 or 3.12 in the uv command above.

To run an example, navigate to the example directory and follow the instructions in the README.

Contributing

We welcome contributions to the repository! Please see the CONTRIBUTING.md file for more information about how to contribute to the repository, requirements, and how to submit an example.