NVIDIA is using GTC to make a broader play for the next phase of enterprise AI: software agents that do more than answer questions. Тhe company unveiled NVIDIA Agent Toolkit, an open-source stack for building and running autonomous enterprise agents, adding a new runtime called OpenShell that is designed to impose policy-based security, privacy and network guardrails on those systems.
The pitch is straightforward: if the first wave of generative AI was about generating text, code and images, the next one is about software that can actually take action inside enterprise systems. NVIDIA is positioning Agent Toolkit as infrastructure for that shift, bundling together Nemotron open models, the AI-Q agent blueprint, open skills such as cuOpt, and the new OpenShell runtime.
NVIDIA CEO Jensen Huang framed the launch as a turning point for enterprise software.
Claude Code and OpenClaw have sparked the agent inflection point — extending AI beyond generation and reasoning into action,
Huang said in the release. He added that employees will increasingly work alongside teams of frontier, specialized and custom-built agents, and argued that enterprise software is set to evolve into “specialized agentic platforms.”
The company is also trying to make the economics look compelling. NVIDIA said its AI-Q blueprint uses frontier models for orchestration and Nemotron open models for research tasks, an approach it claims can cut query costs by more than 50% while still delivering top-ranked performance on DeepResearch Bench and DeepResearch Bench II. That matters because one of the biggest open questions around enterprise agents is not whether they work, but whether they can be deployed at scale without turning inference bills into a budget problem.
Just as important, NVIDIA isn’t presenting this as a solo effort. The company named a long list of software vendors and enterprise platforms that are already integrating parts of the stack, including Adobe, Atlassian, Amdocs, Box, Cadence, Cisco, Cohesity, CrowdStrike, Dassault Systèmes, IQVIA, Red Hat, SAP, Salesforce, Siemens, ServiceNow and Synopsys. The message is classic Nvidia: build the tooling, seed the ecosystem, and make it easier for the rest of the software industry to pull workloads onto Nvidia-backed infrastructure.
There is also a security angle running through the announcement. NVIDIA said OpenShell is being developed with compatibility for cyber- and AI-security tools from providers including Cisco, CrowdStrike, Google, Microsoft Security and TrendAI, underscoring how seriously enterprise buyers are taking the risk of giving autonomous systems access to internal tools and data. Agent systems may be attracting intense interest, but they are also forcing the market to confront a harder question: how much autonomy companies are actually willing to trust in production.
For developers, NVIDIA said Agent Toolkit and OpenShell are available through build.nvidia.com, through inference providers and Nvidia cloud partners including Baseten, Bitdeer AI, CoreWeave, DeepInfra, DigitalOcean, GMI Cloud, Fireworks, Lightning, Together AI and Vultr. The company also said OpenShell can run locally on RTX PCs, workstations and DGX systems. Enterprises, meanwhile, can deploy on infrastructure from AWS, Google Cloud, Microsoft Azure and Oracle Cloud Infrastructure, as well as server vendors including Cisco, Dell Technologies, HPE, Lenovo and Supermicro.
Vendors and what they are using
| Vendor | Nvidia technology mentioned | What the vendor says it is doing |
| Adobe | Agent Toolkit | Using it as a foundation for long-running creativity, productivity and marketing agents in a more secure and cost-efficient environment |
| Amdocs | AI-Q, Nemotron | Powering its Cognitive Core agent platform for monitoring customer interactions and billing data |
| Atlassian | Agent Toolkit, OpenShell | Advancing its Rovo AI agent strategy and AI-powered system of work for Jira and Confluence |
| Box | Agent Toolkit | Enabling enterprise agents using the Box file system to execute long-running business processes securely and reliably |
| Cadence | Agent Toolkit, Nemotron | Supporting ChipStack AI SuperAgent for semiconductor design and verification |
| Cisco | OpenShell | Adding AI Defense protection, controls and guardrails for agent and claw actions |
| Cohesity | OpenShell, AI-Q | Expanding Gaia AI to support more advanced agentic workflows |
| CrowdStrike | AI-Q, OpenShell, Nemotron, NeMo Data Designer | Embedding Falcon protection into Nvidia agent architectures and powering investigative AI workflows |
| Dassault Systèmes | Agent Toolkit, Nemotron | Exploring role-based AI agents, called Virtual Companions, on the 3DEXPERIENCE platform |
| IQVIA | Nemotron, other Agent Toolkit software | Integrating with IQVIA.ai for life sciences use cases across clinical, commercial and real-world operations |
| Palantir | Nemotron | Developing AI agents on Palantir’s sovereign AI operating system reference architecture |
| Red Hat | Agent Toolkit | Integrating it into Red Hat AI Factory with Nvidia for more secure autonomous agents |
| Salesforce | Agent Toolkit, Nemotron | Letting customers build, customize and deploy Agentforce agents for service, sales and marketing |
| SAP | Agent Toolkit, NeMo | Enabling AI agents through Joule Studio on SAP Business Technology Platform |
| Siemens | Nemotron | Launching Fuse EDA AI Agent for semiconductor and PCB workflow orchestration |
| ServiceNow | Agent Toolkit, AI-Q Blueprint, Nemotron | Powering its Autonomous Workforce of AI Specialists |
| Synopsys | Nemotron, Nemo Agent Toolkit | Building a multi-agent framework for semiconductor and systems design |
Image: NVIDIA
