Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
AgentFox serves as an open-source control plane designed for the development and management of AI agents. It systematically catalogs agent repositories while creating a mapping of agents, tools, MCP servers, skills, and handoffs, all without code execution. For the agent frameworks it supports, it enforces tool-access policies, checks tool arguments against predefined limits, and has the capability to pause or deny actions pending human oversight. Runtime evaluations scrutinize model and tool interactions for potential prompt injection and risks of revealing confidential or personal information. Additionally, AgentFox can operate in observation mode prior to activating enforcement, and it meticulously logs policy decisions in a hash-chained audit trail. Developers have the option to install AgentFox using Python or by deploying it through the Docker Compose stack. Its primary audience includes engineering and security teams that require comprehensive visibility, control mechanisms, and verifiable records for managing AI-agent operations. With its release under the Apache-2.0 license, AgentFox also offers a hosted preview for users. This makes it an accessible option for teams looking to enhance their AI workflows with robust management tools.
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.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Model Context Protocol (MCP)
Yes
NVIDIA DOCA
No
NVIDIA OpenShell
No
Integrations
Model Context Protocol (MCP)
No
NVIDIA DOCA
Yes
NVIDIA OpenShell
Yes
Pricing Details
$0
Self-hosted software is free under Apache-2.0. The hosted preview is free while in preview; paid plans are not yet priced.
Free Trial
No
Free Version
Yes
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
Yes
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
No
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
Nometria Inc
Founded
2025
Country
United States
Website
useagentfox.com
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
www.nvidia.com/en-us/solutions/ai/agent-safety/