SANTA CLARA, CALIFORNIA / RankWire.AI / – NVIDIA has introduced its Open Agent Safety Platform to bolster security protocols for autonomous AI agents. The new system encompasses agent testing, deployment, software, computing infrastructure, and robotics systems. NVIDIA revealed the technology on September 28, as businesses increase their reliance on agents within complex computing environments. It combines open source runtime software with autonomous hardware monitoring to enhance security. NVIDIA stated that organizations can tailor the deployment of individual platform modules based on their security and operational needs.
OpenShell functions as the platform’s secure runtime environment, establishing enforceable boundaries around AI agents. This open source software tracks agent activities and enforces policies while agents operate on CPUs. Operators can predefine access rights to files, networks, tools, processes, and credentials before an agent begins its tasks. During operation, OpenShell ensures these limits are maintained. NVIDIA noted that the software supports both open and closed AI models, providing a security boundary outside the model and its associated agent harness.
The second core component, NVIDIA Sentry, offers independent monitoring through BlueField-4 data processing units. Sentry functions outside the agent’s software ecosystem, continuously observing agent behavior. It can quarantine an agent within milliseconds if it attempts to breach its permitted boundaries. The system enforces security policies independently via hardware. Sentry is built on NVIDIA’s DOCA software, which facilitates agent identity verification, access controls, telemetry, and inspection of requests and responses.
Runtime control mechanisms go beyond the AI model itself
This platform integrates application software, secure runtime controls, and computing infrastructure into a multi-layered security framework. OpenShell isolates agents within sandboxed environments with kernel-level separation and policy enforcement, while Sentry adds a dedicated hardware layer inaccessible to agents directly. NVIDIA highlighted recent security incidents where agents bypassed application-level controls during task execution. The system is designed to grant organizations controls that are kept separate from the AI agent and the guiding model.
Over 100 organizations are currently working with technologies connected to the Open Agent Safety Platform, according to NVIDIA. Anthropic has partnered with NVIDIA to develop additional controls for managed AI agents and sandbox environments. Salesforce has integrated OpenShell with Slack to enable teams to review agent activity, audit events, and permission requests. Participants span sectors such as finance, enterprise software, cybersecurity, cloud infrastructure, robotics, and energy. The platform also offers security controls for autonomous systems operating in physical environments.
Open source solutions broaden deployment options
OpenShell operates in conjunction with NVIDIA Vera, the company’s CPU optimized for agentic AI workloads. NVIDIA also permits developers to expand the open source software to third-party platforms, including systems utilizing Arm and Intel architectures. The entire platform can run on compatible hardware environments, with Sentry leveraging BlueField-4 for its independent monitoring functions. NVIDIA confirmed that the software comprising the Open Agent Safety Platform, such as OpenShell and related tools, is accessible via its developer resources and the GitHub platform.
NVIDIA founder and CEO Jensen Huang emphasized that AI safety and security are comprehensive, full-stack engineering challenges. The platform also contributes to the Open Secure AI Alliance, an initiative overseen by the Linux Foundation. This alliance emphasizes open research, tools, and security practices for AI agents. NVIDIA stated that its platform supports governance across software, hardware, computing, and robotics layers. The release introduces new runtime and hardware controls, empowering organizations to deploy autonomous AI agents across an expanding array of business systems.