Open-source Python toolkit (v1.0, 2025) that connects AI agents across LangChain, LlamaIndex, CrewAI, Semantic Kernel, and custom frameworks with unified observability, profiling, and evaluation. Provides OpenTelemetry-compatible tracing, token usage analytics, and workflow composition to help enterprises scale multi-agent systems in production.
NVIDIA NeMo Agent Toolkit (formerly AIQ Toolkit, rebranded in 2025) is an open-source, framework-agnostic Python library released by NVIDIA in March 2025 under the Apache 2.0 license. It lets developers compose, profile, evaluate, and observe AI agent workflows built with any combination of LangChain, LlamaIndex, CrewAI, Microsoft Semantic Kernel, or custom agentic frameworks, treating every agent, tool, and LLM call as a reusable function that can be plugged together without rewriting existing code.
The toolkit is built around five pillars: (1) framework-agnostic function composition so teams can mix LangGraph agents with LlamaIndex retrievers in a single workflow, (2) a built-in profiler that surfaces per-node latency, token cost, and bottlenecks down to the individual LLM call, (3) an evaluation harness with built-in RAGAS, trajectory, and tool-usage metrics, (4) OpenTelemetry-native observability that exports traces to Phoenix, Langfuse, Weights & Biases, Datadog, and any OTLP backend, and (5) reusable plugin components (retrievers, memory, tools) shared across workflows. Configuration is declarative via YAML, and workflows run locally, in containers, or on NVIDIA NIM microservices for GPU-accelerated inference.
Typical adopters are enterprise ML platform teams who have prototyped agents in a single framework and now need production-grade telemetry, cost attribution, and regression testing before scaling to hundreds of concurrent workflows. The toolkit is notable for integrating directly with NVIDIA Blueprints, NIM, and Riva speech services, giving teams that already run on NVIDIA infrastructure a fast path from prototype to production without vendor-locking their agent framework choice. As of April 2026, the GitHub repo (NVIDIA/NeMo-Agent-Toolkit) has over 2,500 stars and ships weekly releases, with active issue response from the NVIDIA team.
Was this helpful?
$0
$4,500 per GPU/year (list)
Ready to get started with NVIDIA NeMo Agent Toolkit?
View Pricing Options âWeekly insights on the latest AI tools, features, and trends delivered to your inbox.
No reviews yet. Be the first to share your experience!
Get started with NVIDIA NeMo Agent Toolkit and see if it's the right fit for your needs.
Get Started âTake our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack âExplore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates âAI agents without memory restart from zero every conversation, wasting time and money. Here's how the three types of agent memory work, why they matter for your business, and which tools actually deliver results in 2026.
Deploy AI agents to production with confidence. Covers containerization, cloud deployment on AWS/Azure/GCP, Kubernetes orchestration, observability, cost control, and security best practices.
Running an online store means juggling product listings, customer questions, inventory, pricing, and marketing â all at once. AI agents can now handle most of it for you. Here's exactly how to automate your e-commerce business without hiring a team.
Compare GPT-4o, Claude 3.5 Sonnet, Gemini 2.0, Llama 4, and more for AI agent workloads. Covers tool calling, reasoning, cost, latency, and which model fits your use case.