Nvidia Nemo Agent Toolkit

What is Nvidia Nemo Agent Toolkit about?

Nvidia Nemo Agent Toolkit is a lightweight, framework‑agnostic library that enables developers to link existing enterprise agents to various data sources, tools, and services. It offers reusable components, profiling, observability integrations, evaluation utilities, and an interactive UI, all while supporting the Model Context Protocol (MCP) for client‑server tool sharing.

How to use Nvidia Nemo Agent Toolkit?

1. Install prerequisites – Git, Git‑LFS, uv, and Python 3.11/3.12.
2. Clone the repository and initialize submodules.
3. Create a virtual environment with uv venv and activate it.
4. Install the library (core only: uv sync; with all plugins and extras: uv sync --all-groups --all-extras).
5. Add needed plugins via uv pip install -e '.[<plugin_name>]' (e.g., langchain).
6. Run workflows using the nat CLI, e.g., nat run --config_file workflow.yaml --input "Your query".
7. Optionally, start the MCP server or client as documented in the docs/source/workflows/mcp folder.

Key features of Nvidia Nemo Agent Toolkit

• Framework agnostic – works with LangChain, LlamaIndex, CrewAI, Semantic Kernel, or custom Python agents.
• Reusable function‑based components – agents, tools, and workflows are plain callable functions.
• Rapid prototyping – pre‑built agents, tools, and workflows can be customized quickly.
• Profiling – detailed token and timing metrics at workflow, tool, and agent levels.
• Observability – integrations for Phoenix, Weave, Langfuse, and OpenTelemetry.
• Evaluation system – built‑in utilities for measuring workflow accuracy.
• User interface – web‑based chat UI for interacting with agents and debugging.
• Full MCP support – act as an MCP client or server to publish/consume remote tools.

Use cases of Nvidia Nemo Agent Toolkit

• Enterprise knowledge assistants – combine internal data stores with LLMs to answer employee queries.
• Tool‑augmented agents – attach search, database, or API tools to agents for complex decision‑making.
• Performance tuning – profile agent workflows to identify bottlenecks before production deployment.
• Observability‑driven monitoring – trace execution across distributed toolchains for compliance and debugging.
• MCP‑based tool sharing – expose proprietary tools via MCP server for consumption by remote agents.

FAQ from the Nvidia Nemo Agent Toolkit

Q: Do I need to replace my existing LangChain or CrewAI code? A: No. The toolkit wraps around existing agents and can be added incrementally.

Q: Which Python versions are supported? A: Python 3.11 and 3.12.

Q: How can I add a custom tool? A: Implement the tool as a regular Python function and register it in the workflow configuration under functions.

Q: Is there a Docker image for the MCP server? A: The repository provides source‑only instructions; you can containerize it yourself using the standard Python base image.

Q: What licensing applies? A: Apache‑2.0.

NVIDIA NeMo Agent Toolkit

NVIDIA NeMo Agent toolkit is a flexible, lightweight, and unifying library that allows you to easily connect existing enterprise agents to data sources and tools across any framework.

[!NOTE] NeMo Agent toolkit was previously known as the Agent Intelligence (AIQ) toolkit, and AgentIQ. The library was renamed to better reflect the purpose of the toolkit and to align with the NVIDIA NeMo family of products. The core technologies, performance and roadmap remain unchanged and the API is fully compatible with previous releases.

The rename is still in progress and references to the previous name may still be found in the codebase and documentation.

Key Features

• Framework Agnostic: NeMo Agent toolkit works side-by-side and around existing agentic frameworks, such as LangChain, LlamaIndex, CrewAI, and Microsoft Semantic Kernel, as well as customer enterprise frameworks and simple Python agents. This allows you to use your current technology stack without replatforming. NeMo Agent toolkit complements any existing agentic framework or memory tool you're using and isn't tied to any specific agentic framework, long-term memory, or data source.

• Reusability: Every agent, tool, and agentic workflow in this library exists as a function call that works together in complex software applications. The composability between these agents, tools, and workflows allows you to build once and reuse in different scenarios.

• Rapid Development: Start with a pre-built agent, tool, or workflow, and customize it to your needs. This allows you and your development teams to move quickly if you're already developing with agents.

• Profiling: Use the profiler to profile entire workflows down to the tool and agent level, track input/output tokens and timings, and identify bottlenecks. While we encourage you to wrap (decorate) every tool and agent to get the most out of the profiler, you have the freedom to integrate your tools, agents, and workflows to whatever level you want. You start small and go to where you believe you'll see the most value and expand from there.

• Observability: Monitor and debug your workflows with dedicated integrations for popular observability platforms such as Phoenix, Weave, and Langfuse, plus compatibility with OpenTelemetry-based observability platforms. Track performance, trace execution flows, and gain insights into your agent behaviors.

• Evaluation System: Validate and maintain accuracy of agentic workflows with built-in evaluation tools.

• User Interface: Use the NeMo Agent toolkit UI chat interface to interact with your agents, visualize output, and debug workflows.

• Full MCP Support: Compatible with Model Context Protocol (MCP). You can use NeMo Agent toolkit as an MCP client to connect to and use tools served by remote MCP servers. You can also use NeMo Agent toolkit as an MCP server to publish tools via MCP.

With NeMo Agent toolkit, you can move quickly, experiment freely, and ensure reliability across all your agent-driven projects.

Component Overview

The following diagram illustrates the key components of NeMo Agent toolkit and how they interact. It provides a high-level view of the architecture, including agents, plugins, workflows, and user interfaces. Use this as a reference to understand how to integrate and extend NeMo Agent toolkit in your projects.

Links

• Documentation: Explore the full documentation for NeMo Agent toolkit.
• Get Started Guide: Set up your environment and start building with NeMo Agent toolkit.
• Examples: Explore examples of NeMo Agent toolkit workflows located in the examples directory of the source repository.
• Create and Customize NeMo Agent toolkit Workflows: Learn how to create and customize NeMo Agent toolkit workflows.
• Evaluate with NeMo Agent toolkit: Learn how to evaluate your NeMo Agent toolkit workflows.
• Troubleshooting: Get help with common issues.

Get Started

Prerequisites

Before you begin using NeMo Agent toolkit, ensure that you meet the following software prerequisites.

• Install Git
• Install Git Large File Storage (LFS)
• Install uv (version 0.5.4 or later, latest version is recommended)
• Install Python (3.11 or 3.12)

Install From Source

1. Clone the NeMo Agent toolkit repository to your local machine.

   git clone git@github.com:NVIDIA/NeMo-Agent-Toolkit.git nemo-agent-toolkit
   cd nemo-agent-toolkit
   

2. Initialize, fetch, and update submodules in the Git repository.

   git submodule update --init --recursive
   

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

   git lfs install
   git lfs fetch
   git lfs pull
   

4. Create a Python environment.

   uv venv --seed .venv
   source .venv/bin/activate
   

   Make sure the environment is built with Python version 3.11 or 3.12. If you have multiple Python versions installed, you can specify the desired version using the --python flag. For example, to use Python 3.11:

   uv venv --seed .venv --python 3.11
   

   You can replace --python 3.11 with any other Python version (3.11 or 3.12) that you have installed.

5. Install the NeMo Agent toolkit library. To install the NeMo Agent toolkit library along with all of the optional dependencies. Including developer tools (--all-groups) and all of the dependencies needed for profiling and plugins (--all-extras) in the source repository, run the following:

   uv sync --all-groups --all-extras
   

   Alternatively to install just the core NeMo Agent toolkit without any plugins, run the following:

   uv sync
   

   At this point individual plugins, which are located under the packages directory, can be installed with the following command uv pip install -e '.[<plugin_name>]'. For example, to install the langchain plugin, run the following:

   uv pip install -e '.[langchain]'
   

   [!NOTE] Many of the example workflows require plugins, and following the documented steps in one of these examples will in turn install the necessary plugins. For example following the steps in the examples/getting_started/simple_web_query/README.md guide will install the nvidia-nat-langchain plugin if you haven't already done so.

   In addition to plugins, there are optional dependencies needed for profiling. To install these dependencies, run the following:

   uv pip install -e '.[profiling]'
   

6. Verify the installation using the NeMo Agent toolkit CLI

   nat --version
   

   This should output the NeMo Agent toolkit version which is currently installed.

Hello World Example

1. Ensure you have set the NVIDIA_API_KEY environment variable to allow the example to use NVIDIA NIMs. An API key can be obtained by visiting build.nvidia.com and creating an account.

   export NVIDIA_API_KEY=<your_api_key>
   

2. Create the NeMo Agent toolkit workflow configuration file. This file will define the agents, tools, and workflows that will be used in the example. Save the following as workflow.yaml:

   functions:
      # Add a tool to search wikipedia
      wikipedia_search:
         _type: wiki_search
         max_results: 2
   
   llms:
      # Tell NeMo Agent toolkit which LLM to use for the agent
      nim_llm:
         _type: nim
         model_name: meta/llama-3.1-70b-instruct
         temperature: 0.0
   
   workflow:
      # Use an agent that 'reasons' and 'acts'
      _type: react_agent
      # Give it access to our wikipedia search tool
      tool_names: [wikipedia_search]
      # Tell it which LLM to use
      llm_name: nim_llm
      # Make it verbose
      verbose: true
      # Retry up to 3 times
      parse_agent_response_max_retries: 3
   

3. Run the Hello World example using the nat CLI and the workflow.yaml file.

   nat run --config_file workflow.yaml --input "List five subspecies of Aardvarks"
   

   This will run the workflow and output the results to the console.

   Workflow Result:
   ['Here are five subspecies of Aardvarks:\n\n1. Orycteropus afer afer (Southern aardvark)\n2. O. a. adametzi  Grote, 1921 (Western aardvark)\n3. O. a. aethiopicus  Sundevall, 1843\n4. O. a. angolensis  Zukowsky & Haltenorth, 1957\n5. O. a. erikssoni  Lönnberg, 1906']
   

Feedback

We would love to hear from you! Please file an issue on GitHub if you have any feedback or feature requests.

Acknowledgements

We would like to thank the following open source projects that made NeMo Agent toolkit possible:

• CrewAI
• FastAPI
• LangChain
• Llama-Index
• Mem0ai
• Ragas
• Semantic Kernel
• uv