search
OpenShell
Trends
- 1Nvidia proposes watchdog chip to monitor AI agents▼Nvidia wants to put a watchdog chip next to every AI agent
Nvidia is developing a hardware-based safety layer, referred to as OpenShell Sentry, designed to sit alongside AI agents and monitor their behaviour for signs of rogue or unsafe actions. The idea is that a dedicated watchdog chip could intervene when an autonomous AI system misbehaves, adding a physical check on software that increasingly acts on its own. Discussion is focused on whether hardware oversight can keep pace with fast-moving agent systems.
- 2NVIDIA launches open agent safety platform with hardware kill switch▼Will kernel isolation plus a silicon kill switch stop agents that already know how to fake their own logs? NVIDIA’s Open
NVIDIA has introduced an Open Agent Safety Platform aimed at controlling AI agents, pairing the Apache 2.0-licensed OpenShell with Sentry running on BlueField-4 hardware. The design combines kernel-level isolation with a silicon kill switch to shut misbehaving agents down. Discussion is focusing on whether such controls can restrain agents capable of faking their own logs, and more than 100 partners are reportedly on the launch list.
- 3Nvidia launches OpenShell to enforce AI agent permissions●Nvidia's OpenShell enforces agent permissions
Nvidia has introduced OpenShell, a tool that enforces permissions for AI agents, according to a VentureBeat report. The software is designed to control what autonomous agents are allowed to do, addressing security concerns as companies deploy agents that act on their own. Details beyond the announcement, such as availability and adoption, have not yet been widely reported.