Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
The NVIDIA Open Agent Safety Platform serves as an open reference framework designed to monitor and manage the behavior of AI agents continuously, ensuring that organizations can maintain agents that are isolated, observable, auditable, and operate within set boundaries. This platform integrates real-time governance, ongoing threat detection, and the enforcement of policies through hardware isolation, providing robust protection for enterprise AI agents from the initial testing phases all the way to deployment. The NVIDIA OpenShell contributes to this by offering an open-source runtime that differentiates the execution of agents from their access to data, tools, and outside systems, utilizing sandboxed environments and a zero-trust policy approach to strictly regulate agents' visibility, actions, and interactions. Policies are enforced externally to the agent process, effectively mitigating the risks associated with unpredicted behavior. Furthermore, NVIDIA Sentry enhances security by adding an extra layer that meticulously monitors agent requests and responses, verifies agent identities, and continuously manages access to data, tools, APIs, and services while also having the capability to isolate agents when necessary. This comprehensive approach ensures that organizations can safeguard their AI agents while promoting a secure and controlled operational environment.
Description
NVIDIA OpenShell serves as an open and secure runtime environment specifically designed for autonomous AI agents, regulating their execution, access rights, and the pathways for inference traffic. Instead of embedding security within the model or application, it maintains safety measures in the surrounding environment, meaning that nothing is allowed by default; permissions are assigned through established policies, and enforcement mechanisms operate outside the agent process to prevent any circumvention via prompts. Each autonomous agent operates within a confined sandbox, which restricts direct network connectivity, limits file access, and implements kernel-level monitoring of system calls to ensure rigorous oversight. Acting as the control plane, a gateway is responsible for user authentication, lifecycle management of sandboxes, and the provision of policies, settings, credentials, and inference configurations to the agents. Additionally, a supervisor operates externally to each sandbox, scrutinizing network requests according to policies at various levels—including binary, destination, method, and path—and only grants access to credentials when explicitly permitted, thus enhancing the overall security framework. This layered architecture ensures that the agents function effectively while maintaining robust security protocols throughout their operations.
API Access
Has API
Yes
API Access
Has API
No
Integrations
NVIDIA DOCA
Yes
NVIDIA Open Agent Safety Platform
No
NVIDIA OpenShell
Yes
Integrations
NVIDIA DOCA
No
NVIDIA Open Agent Safety Platform
Yes
NVIDIA OpenShell
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
www.nvidia.com/en-us/solutions/ai/agent-safety/
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
www.nvidia.com/en-us/ai/openshell/