NVIDIA launches Open Agent Safety Platform: kernel-level sandboxing plus BlueField DPU monitoring
firstadopter · x · 2026-09-28
NVIDIA announced the Open Agent Safety Platform, a layered safeguard for AI agents spanning software and hardware:
- OpenShell: an open-source secure runtime executing autonomous agents in sandboxed environments with kernel-level isolation
- NVIDIA Sentry: runs on BlueField-4 DPUs, using DOCA to correlate agent interactions, policy decisions, and tool access into contextual activity records
- Architecture: five principles — verifiable policy, out-of-band enforcement, controlling the path to the model, scaling agent authority with reasoning visibility, and a shared responsibility model across labs, enterprises, and hardware providers
In Vera Rubin POD systems, BlueField-4 DPUs sit on the node's only path to the model, enabling continuous out-of-band observability and real-time policy enforcement at line speed. The platform is also compatible with other hardware systems.
Related event: NVIDIA Launches Open Agent Safety Platform with 100+ Partners(35 posts)→
More from Infra
- India's Sarvam launches Token Factory, hosting top open models on local infra — HarveenChadha · 2026-11-16
- Gemini 3.5 Flash now runs on air-gapped Google Distributed Cloud, offline up to 12 months — shashib · 2026-11-16
- Gemma.c: full Gemma 1/2/3 multimodal inference in a single C file, ~72 tok/s on CPU at INT8 — This-Purchase-3325 · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Jailbroken PS4 runs a 9B open-source model at up to 43 tok/s by talking directly to its 2013-era GPU — AIFlow_ML · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16