NVIDIA Opens Early Access to Factory Agent Blueprint as European Industry Adopts It

NVIDIA has made its Factory Operations Blueprint (FOX) available in early access on GitHub, giving developers a path to build always-on factory manager agents. At GTC Berlin, the company also detailed how European industrial firms use its CUDA-X, Omniverse, Cosmos and Nemotron technologies in engineering and manufacturing.
- NVIDIA's Factory Operations Blueprint (FOX) is in early access on GitHub for building factory manager and specialist agents.
- Siemens cites estimated cost savings of 20% and a 40% cut in inspection calibration time at its Erlangen factory.
- cuDSS reaches general availability at GTC Berlin.
- imec benchmarks show up to 40x speedup, and Infineon reports a 12x speedup in 3D breakdown simulation.
- Audi, Schaeffler, Wandelbots and Schneider Electric use Omniverse and Isaac for digital twins and robot simulation.
FOX: agents for the factory floor
According to NVIDIA, the Factory Operations Blueprint lets developers build and deploy factory manager agents that coordinate work across machines. Alongside them sit specialist agents for use cases such as visual inspection, root cause analysis, report generation and fleet management.
The agents can connect to frontier models, including NVIDIA Cosmos and Nemotron, and to foundational knowledge such as computer-aided design, product lifecycle management, simulation software, and IT and operational technology systems. NVIDIA says the blueprint lets the ecosystem build industrial agents that monitor factory operations in real time, correlate visual findings with machine logs to investigate problems, and coordinate responses. With Cosmos in-context learning, the agents can adapt using examples and documentation, without fine-tuning.
Siemens is integrating agents built with FOX into Intelligence Center X, its agentic enterprise system, to help identify root causes and coordinate factory operations, for estimated cost savings of 20%. Siemens' Process Preparation X agents use NVIDIA Cosmos Data Factory tools and skills to generate defect images for circuit-board inspection. At its Erlangen electronics factory, Siemens used this approach to reduce calibration time of inspection processes by 40%.
Faster simulation from the first design
NVIDIA is releasing cuDSS for general availability at GTC Berlin. The library accelerates the calculations behind simulations of structural stress, fluid flow, electromagnetic fields and semiconductor device behavior.
- Mercedes-Benz uses Siemens' Simcenter STAR-CCM+ on NVIDIA GPUs to compare vehicle designs through faster aerodynamic simulations. In its factories it applies NVIDIA Cosmos 3 and the Metropolis VSS blueprint to build agents for vehicle inspection and windshield assembly verification.
- imec and Infineon use Synopsys software with NVIDIA accelerated computing. Benchmarks of S-Litho on imec's model show up to 40x speedup, while Infineon reports a 12x speedup in 3D breakdown simulation for next-generation power devices using Sentaurus Device.
- Autodesk brings the NVIDIA PhysicsNeMo and Warp frameworks into NavPack, integrated with Autodesk Alias, to help designers such as those at Bentley's predict vehicle performance.
- Cadence is benchmarking automotive fluid-dynamics workloads on NVIDIA GPUs.
- Leonardo works with Neural Concept on AI-driven aircraft design using Omniverse libraries.
Dassault Systèmes' LEO & AURA Virtual Companions, powered by Nemotron, help car manufacturers design and virtually test vehicle doors before building physical prototypes. UniversalAGI is working with Saab on physics AI models, accelerated by NVIDIA Warp, to evaluate thousands of wave conditions and headings in real time instead of days, so vessels can anticipate dangerous motion and select safer routes. PhysicsX is working with GB1, Britain's America's Cup team, on yacht design, and Fermioniq's Sofia agent helps Deltares and Dutch ministries model river flow. Mistral plans to use CUDA-X, Warp and Omniverse libraries to accelerate physics simulation and generate training data for engineering AI models.
Testing factories and robots virtually
NVIDIA Omniverse and Isaac libraries support digital twins and robotics simulation, so manufacturers can evaluate production systems and robot behavior before changing anything on the factory floor.
Audi uses a battery-production digital twin built with Omniverse libraries to test production concepts before physical equipment is available. It is also working with Dassault Systèmes and Agile Robots to simulate and validate mobile humanoid robots and logistics processes in DELMIA virtual twins. Schaeffler is integrating digital twins of its humanoid actuators with NVIDIA Isaac simulation frameworks to reduce physical testing, and Wandelbots uses NOVA with Isaac Sim to validate assembly workflows digitally.
Falkor, a KONGSBERG company, is integrating agents and Omniverse libraries into its platform. With Microsoft Azure NCv6 virtual machines powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, its agents combine engineering data, operating information and 3D equipment geometry to support inspection and maintenance in the process and energy industries. Schneider Electric and AVEVA are developing an AI factory digital twin for Nscale to help engineers compare power, cooling and equipment configurations before making physical changes.
What it means for industry
The FOX blueprint is only in early access, so its practical reach will depend on how many developers and software vendors build on it. The figures in the announcement, including Siemens' estimated 20% cost savings and 40% shorter calibration time, are reported by NVIDIA and its partners and come from specific deployments. The examples show European manufacturers applying simulation, digital twins and agents from design through the factory floor, with many of the efforts running on NVIDIA software and GPUs.

