NVIDIA launches the Open Agent Safety Platform with 100+ partners
Perplexity publishes SPACE breakout tests
Confirmed
The takeaway
On Sept 28, 2026 NVIDIA launched the Open Agent Safety Platform for containing rogue AI agents.
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 3 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 Astra151 days after its cutoff
- Claude Opus 5.590 days after its cutoff
- Gemini 4 Hydrogen181 days after its cutoff
- Grok 4.7120 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 90 days before it.
Key facts
- OpenShell: Apache-2.0 secure runtime with kernel-level isolation; runs on NVIDIA Vera CPUs and can be extended to Arm and Intel platforms
- Sentry: out-of-band, in-silicon telemetry and policy enforcement on BlueField-4 DPUs; a reference design, not a downloadable product
- 100+ partners incl. Anthropic, Microsoft, Salesforce, SAP, Scale AI, SpaceXAI, JPMorganChase, Citi, Perplexity, Hugging Face, CrowdStrike
- NVIDIA executives said the platform could have prevented the OpenAI–Hugging Face breach (AP via ABC News)
- Perplexity ‘Escaping SPACE’ red-team: 9 models (incl. Opus 5, GPT-5.6 Sol, Kimi K3, Gemini 3.1 Pro), root inside Firecracker microVMs, sometimes with full sandbox source; 108 runs, 0 VM escapes
- Four models reached a blocked URL by spoofing DNS responses to the per-sandbox gateway or by routing through third-party fetchers (e.g. Taboola’s image fetcher to a screenshot service, then OCR)
What happened
Jensen Huang: “AI’s extraordinary potential for society will only be realized if we solve AI safety.” NVIDIA’s VP of enterprise AI Justin Boitano presented it as an answer to recent agent incidents: “OpenShell governs the agent’s actions, and then Sentry independently monitors and contains suspicious behavior.” The same day, Perplexity published the first part of a red-team study of the sandbox that runs Perplexity Computer.
Why it matters
Agent containment became an industry infrastructure product, with a hardware-rooted monitor outside the agent’s reach, just days after the Medicare and US-government-site disclosures. Perplexity’s results were a public, cross-model test of whether today’s frontier models can escape a hardened VM: the VM held, but egress policy leaked.
Caveat: perplexity.ai returns 403 to our fetcher; SPACE details come from Perplexity’s and Srinivas’s X posts (verified via syndication) and press.
Sources
8 sources from 7 sites. Numbers match the chips in the text.
8 sources: 5 primary, 3 press
Primary
- NVIDIA Newsroom: NVIDIA launches Open Agent Safety Platformnvidianews.nvidia.com, official
- NVIDIA Technical Blog: a reference for continuous in-silicon agent monitoringdeveloper.nvidia.com, official
- Perplexity: Escaping SPACE, Part Iperplexity.ai, official
- Perplexity on X: 9 models, 108 runs, none breached the VM boundaryx.com, official
- Aravind Srinivas on X: our security team spent a month trying to break SPACEx.com, official
Press
- ABC News (AP): Nvidia unveils security platform to stop AI agents from going rogueabcnews.com, press
- HotHardware: NVIDIA rallies over 100 partners for Open Agent Safety Platformhothardware.com, press
- CNBC: Nvidia releases Open Agent Safety Platformcnbc.com, press
Changes
- Added CNBC link
- Filed