Project
NVIDIA's secure runtime for AI agents, which contains them within a defined boundary and enforces policy and governance over what they can access and do.
Perplexity has open-sourced SPACE, an isolation sandbox for AI agents that CoreWeave, Akamai and Crusoe already deploy. SiliconANGLE reports that Perplexity's own test found no escape across 118 attempts by nine frontier models.
Reality
nFOX Lab plans to release Blockhouse, a kernel-level sandbox that removes a self-hosted AI model's privileges by default, under the Apache 2.0 license. For now it is available as a beta for qualified enterprise evaluations.
Reality
ServiceNow announced AI Passport, a cryptographically signed credential that sets what each AI agent and MCP server may do at every step of a workflow. The prevention claims are ServiceNow's own description of a design.
Reality
NVIDIA put its Sentry agent watchdog on separate BlueField 4 chips that can quarantine an agent in milliseconds, a day before OpenAI launched always-on Dots. An agent with no finish line gets no scheduled human review, so its rules need an enforcer the agent cannot edit.
Perspective Coverage
13 publishersReality
Nvidia says over 100 organizations use OpenShell, an open-source agent sandbox whose Sentry quarantine layer runs on its BlueField-4 chips. The free half enforces the access list a team writes; stopping a rogue agent fast means running Nvidia hardware.
Perspective Coverage
11 publishersReality
Intel has added NVIDIA's Apache-2.0 OpenShell policy layer to its enterprise agent toolkit, putting sandboxing and kernel-level agent controls on Xeon. The feature ships switched off, so what it is worth to Intel depends on how many agent teams turn it on.
Reality
Nvidia launched its Open Agent Safety Platform with more than 100 partners, pairing two open-source agent-containment tools with its own chips. Because anyone can use the code, whatever Nvidia earns from the platform has to arrive as processor sales to the labs that adopt it.
Perspective Coverage
14 publishersReality
Nvidia says its new agent safety platform could have stopped OpenAI's agents breaching Hugging Face, a company it agreed to buy for $12.9 billion. Neither that claim nor the speed of its Sentry hardware watchdog has been independently tested.
Perspective Coverage
9 publishersReality
Palo Alto Networks lined up four agent-security components with NVIDIA's Open Agent Safety Platform, and two are available today. Buyers can deploy network enforcement on BlueField processors now. The Vera-CPU gateway and identity controls for agent sandboxes are still plans.
Reality
NVIDIA's Open Agent Safety Platform, launched September 28, makes its OpenShell runtime available now while its Sentry hardware watchdog has no release date. Sentry's promised millisecond stop has no independent test yet, so the hardware half rests on NVIDIA's word.
Perspective Coverage
4 publishersReality
A post from NVIDIA's AI safety and security teams cites three summer reports of frontier agents leaving their boundaries, and argues only infrastructure can hold final authority.
Reality