NVIDIA AgentIQ Toolkit

See AgentIQ in Action

How AgentIQ Works

NVIDIA AgentIQ is a toolkit that enables developers across the organization to connect their own personalized, intelligent agents and integrate them into customized workflows. Ease the development and evaluation of accelerated agentic systems with tools provided in the open-source library.

Simplify Development: Experiment and prototype new agentic AI applications quickly and easily with AgentIQ’s configuration builder. With universal descriptors for agents, tools, and workflows, you can flexibly choose and connect agent frameworks best suited to each task in a workflow. Access a reusable collection of tools, pipelines, and agentic workflows to ease the development of agentic AI systems.

Access a Collection of Tools: Build agentic systems with ease. Use the best retrieval-augmented generation (RAG) architectures, workflows, and search tools available across your organization, or leverage NVIDIA AI Blueprints, built with NVIDIA NIM? and NeMo?, to build a highly accurate, scalable RAG pipeline, a digital human communication interface, or an AI agent for research and reporting.

Accelerate Agent Responses: Use fine-grained telemetry to enhance agentic AI workflows. This profiling data will be used by NVIDIA NIM and NVIDIA Dynamo to optimize the performance of agentic systems. These forecasted metrics—which can include details about an inference call to an LLM for a particular agent, such as what prompt is in memory, where it might reside, and which other agents are likely to call it—can be used to drive a more efficient workflow, enabling better business outcomes without requiring an upgrade to underlying infrastructure.

Increase Accuracy: Evaluate an agentic system’s accuracy using metrics collected with the AgentIQ toolkit, and connect them with your observability and orchestration tools. Understand and debug inputs and outputs for each component in an agentic workflow and identify areas for improvement. Swap out tools or models and use the AgentIQ toolkit to quickly reevaluate the pipeline to understand its impact.

Get Started With AgentIQ

# Clone the repo:
git clone git@github.com:NVIDIA/AgentIQ.git 
cd agentiq

# Initialize the Git repository:
git submodule update --init --recursive

# Download the datasets:
git lfs install
git lfs fetch
git lfs pull

# Create a Python environment:
uv venv --seed .venv
source .venv/bin/activate
uv sync --all-groups --all-extras

# Verify the library installation:
aiq --help
aiq --version

pip install agentiq

# Verify the library installation:
aiq --help
aiq --version

AgentIQ Learning Library

Ethical AI

NVIDIA believes trustworthy AI is a shared responsibility, and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure their model meets the requirements for the relevant industry and use case and addresses unforeseen product misuse.

For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety and Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.