Corroborated event · 7 outlets
Nvidia launched a platform of software and hardware products that add independent security layers around AI agents, following agent security breaches.
AI brief
Nvidia introduced an open-source software tool designed to keep AI agents from escaping containment, following a series of high-profile AI safety incidents.
Why it matters: It offers a freely available way to limit the risk of AI agents acting outside their intended boundaries.
Written by AI from WIRED AI's published text.
Background
From our own funding, model and news trackers, not from the source.
NVIDIA
- Newest model on the API
- Nemotron 3.5 Super VL · 15 Oct 2026 · $0.15 in / $0.5 out per million tokens
- Last 30 days
- 67 news stories
More coverage of this story (7)
Nvidia launches AI agent security platform
Nvidia launches new platform for reining in rogue AI agents
TechCrunch AI · 28 Sept 2026, 18:31
AI agents are going rogue and causing new security headaches — but Nvidia has a way to stop them
Tom's Guide AI · 28 Sept 2026, 16:30
Nvidia unveils security platform to rein in AI agents and $150bn stock buyback
Guardian AI · 28 Sept 2026, 15:32
Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips
The Decoder · 28 Sept 2026, 14:32
Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
The Verge AI · 28 Sept 2026, 13:36
NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring
NVIDIA Developer Blog · 28 Sept 2026, 08:57
Add Runtime Controls to AI Agents with NVIDIA OpenShell
NVIDIA Developer Blog · 28 Sept 2026, 08:40
Primary source
“In the wake of a series of high-profile AI safety incidents, Nvidia is introducing a new software tool that helps keep agents from escaping containment.”
Reporting from a publisher outside the organisation being covered.
Read original story ↗