Az Nvidia kiadta az OpenShell Reference Architecture nevű keretrendszert, amely segít a vállalatoknak biztonságos korlátok között tartani az autonóm AI-ügynököket. Az architektúra a nyílt forráskódú OpenShell futtatókörnyezetre épül, és az infrastruktúra szintjén biztosítja az ügynökök ellenőrzését, az azonosítást, valamint a hozzáférési szabályok betartatását.
A megoldás a szandboxos elkülönítésen túl a hálózati és jogosultsági határokat is felügyeli. Az elgondolás működtetéséhez speciális Nvidia hardveres infrastruktúrára van szükség, beleértve a cég hálózati felügyeletért felelős BlueField egységeit és Sentry biztonsági szoftverét.
Az Nvidia többek között az Amazon Web Services, a Canonical, a Red Hat, valamint olyan pénzintézetek partnerségével indítja el a modellt, mint a BBVA és a Santander. A rendszer a főbb fejlett modellekkel, köztük az OpenAI, az Anthropic és a Meta rendszereivel is együttműködik.
Az eredeti szöveg (The Register)
Give your agents freedom to do useful work by locking them down
Nvidia has proposed a new way to keep corporate AI agents in line.
Nvidia on Wednesday introduced its OpenShell Reference Architecture. Based on the company's OpenShell secure runtime, It's a recipe for creating, operating, observing, and policing AI agents using OpenShell on Nvidia hardware.
"Nvidia created OpenShell to give agents the freedom to do useful work within clearly defined boundaries — contained, monitored and under control," CEO Jensen Huang said in a canned statement. "With the OpenShell Reference Architecture, agents can think on Rubin, act on Vera and be governed on BlueField."
AI agents are touted as a powerful automation technology. The reality is that they can be unruly, as demonstrated by security testing OpenAI and Anthropic conducted, during which their models exceeded their remit and attacked third-party organizations.
Developers of existing agents, like Claude Code, Codex, OpenClaw, and OpenCode, therefore include controls that limit access to tools like curl and bash.Devs also create sandboxes to isolate an agentic process from the host, so that if agents go awry they're contained.
OpenShell sits a level above that with a runtime that extends sandboxing to govern gateway-brokered credentials, identity and policy boundaries, and (eventually) routing and workflows too.
At least mostly – OpenShell still has a few open security-related issues listed on GitHub.
To implement OpenShell, organizations need Nvidia hardware. The company's blueprint calls for Nvidia Vera Rubin infrastructure to run models like Nvidia Nemotron, with agent harnesses handled via Vera CPUs, and Nvidia BlueField-4 DPUs (aka SmartNICs) propping up Nvidia Sentry security software to monitor agent behavior.
The AI biz has made this blueprint available to partners capable of powering Linux and Kubernetes infrastructure. The usual suspects are aboard: Canonical, SUSE and Red Hat. Cloud hyperscalers Amazon Web Services, Google Cloud, and Microsoft Azure have also been tapped as vendors for this vision.
And of course Nvidia's floor plan applies to agents from various model builders, including Anthropic, Cohere, Google, Meta, OpenAI, Perplexity, Reflection, and SpaceX.
Nvidia says several banks – Europe’s BBVA and Santander – are perusing the OpenShell Reference Architecture spec to see how it aligns with their security and governance requirements. And the AI biz is not too modest to let slip that SAP is integrating the OpenShell Reference Architecture with its Joule Studio runtime for safer agent operations.
It's worth noting that OpenShell collects telemetry data by default, "to improve the project," Nvidia insists. The biz allows users to opt-out, with a cautionary note: "Third-party services, model providers, inference endpoints, agents, or tools that you configure and use with OpenShell may have their own terms and privacy practices." ®
Give your agents freedom to do useful work by locking them down
GPUzilla boasts modular bit barns could speed up deployments from six months to just two weeks
The first technology created with a self-disrupt button... But why oh why didn't they call Claude clone Fauxtoshop?
Commission opens DSA probe into fake listings and phishing on the platform, says its fraud defenses 'absolutely substandard'
