Gecko Robotics partners with NVIDIA to integrate AI agent security and control

Gecko Robotics is leveraging NVIDIA’s latest agentic AI security layer within its inspection robot fleet. Source: Gecko Robotics

NVIDIA Corp. unveiled its Open Agent Safety Platform today, featuring the open-source OpenShell software and the Sentry reference system design. These tools are designed to enhance governance and control across hardware, compute, and software layers for robots operating AI agents. Gecko Robotics Inc. is among the more than 100 organizations collaborating with NVIDIA’s technology.

Following recent incidents where AI agents from OpenAI bypassed application-level controls to attack Hugging Face, developers in the AI and robotics sectors have intensified efforts to establish traceability, accountability, and preventative security measures.

“As we continue to discover the frontier of AI capabilities, we must accelerate discovery at the frontier of AI safety,” said Jensen Huang, CEO of NVIDIA. “Safety and security require full-stack engineering. The NVIDIA Open Agent Safety Platform brings together industry, researchers, and public-sector organizations to share best practices, align on resolution methods, and foster international cooperation.”

Editor’s note: Physical AI is a key topic track at RoboBusiness 2026, taking place on Oct. 20 and 21 in Santa Clara, Calif. Register now to attend.

NVIDIA OpenShell and Sentry enforce policy

OpenShell provides a secure runtime boundary that traces all actions and enforces policy as AI agents operate on NVIDIA Vera CPUs. According to NVIDIA, it offers deterministic governance for agent execution, access, and inference routing.

As open-source software, OpenShell can be extended to work with third-party compute platforms, including those from Arm and Intel, the Santa Clara, Calif.-based company added.

NVIDIA Sentry adds an out-of-band watchdog running on BlueField-4 data-processing units (DPUs) to continuously monitor agent behavior. The company stated that Sentry monitors outcomes against policies and can quarantine agents attempting to breach boundaries in milliseconds.

“For the agent economy to grow, we need a trusted foundation across silicon and software,” said Justin Boitano, vice president of enterprise AI at NVIDIA, during a press briefing. “We want to engage everybody to advance a new layer of agent security.”

“The independent trust domain is like how self-driving cars work,” he explained. “The primary system runs perception, and a safety island ensures that the overall system fails safely. The same principles apply to frontier AI systems.”

OpenShell can offload security onto silicon or DPUs as needed, while Sentry monitors reasoning traces. A Policy Prover within the NVIDIA Open Agent Safety Platform is deterministic and operates at high speed.

“If you write a policy that says an agent can’t read code from Github, an agent could spawn separate subagents to read it and then post that information, with fleets superseding global policies,” said Boitano. “The Policy Prover validates the master decision tree, looking at combined file and network access to find unintended exfiltration. It comes out of AWS’s S3 research to create verifiable policies.”

“We see long-term agent behavior to be a different problem than sandboxing,” he added. “OpenShell is projecting the intent of a policy into infrastructure.”

The NVIDIA Open Agent Safety Platform includes OpenShell and Sentry. Source: NVIDIA

Gecko gives AI agent control over robot motion

While recent security incidents occurred entirely within software, Gecko Robotics noted they revealed a potential vulnerability affecting all AI agents, including robots. The company has used NVIDIA OpenShell to explore how enforceable boundaries can keep AI-powered robots operating within human-defined permissions. Gecko aims to establish the safeguards necessary to deploy greater autonomy responsibly.

“As Jensen says, safety is an engineering problem, not a legal one,” said Jake Loosararian, co-founder and CEO of Gecko Robotics. “The idea that losing control of AI is inevitable is a dangerous excuse for inaction. We have a responsibility to build safeguards that keep AI within the boundaries humans set.”

“What NVIDIA has built with their Open Agent Safety Platform, and Gecko is testing for robots, is confronting the risk before it reaches the physical world and helping ensure greater autonomy does not come at the expense of human control,” he added.

Gecko utilizes robots capable of climbing, crawling, flying, and swimming on critical infrastructure for Fortune 100 energy companies, as well as the U.S. Air Force and U.S. Navy. Its systems inspect everything from fuel tanks to nuclear submarines and aircraft carriers.

Ariel Weingarten, director of engineering at Gecko, told The Robot Report that its agents have access to the same system commands as its field operators, including:

They do not handle the data lifecycle or uploading to Gecko’s governance cloud, he said.

While research on AI agent security continues, Pittsburgh-based Gecko is using NVIDIA OpenShell to create secure runtime boundaries that developers can use to define permissible actions and restrictions.

Komodo robot includes enforcement layer

Gecko’s Komodo, a robot deployed with the U.S. Navy, places an independent enforcement layer between the AI agent and the hardware. “The developer decides what Komodo should do; OpenShell ensures it stays within the rules,” said the company.

“Physical AI and robotics represent the next frontier of technology,” asserted Gecko Robotics. “Moving intelligence from software into machines also brings greater responsibility. Model-level safety alone is not enough.”

Because Gecko already follows well-defined security controls for U.S. military assets, implementing them in OpenShell was less of a challenge, said Weingarten.

“By building enforceable controls across the full technology stack, NVIDIA and Gecko are helping ensure the safeguards governing physical AI advance as quickly as the technology itself,” the company added.

Gecko’s Cantilever AI-powered platform transforms the massive datasets collected by its robots into actionable insights. The company claimed that its systems enable data-driven, evidence-based decisions on structures, delivering a return on investment (ROI) for customers.

Since OpenShell operates within the boundary of a Komodo field system, it does not directly interact with Cantilever, noted Weingarten. Gecko intends to use NVIDIA’s security layer for both defense and military systems in the future, he said. The deterministic control could also benefit swarm-level operations.

“It is certainly helpful to have invariants at the individual unit level that can be used to reason about swarm/fleet dynamics,” Weingarten said. “We’re excited to evolve as we move from individual system control to agentic-assisted operation of an entire deployment.”