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
Vulnify serves as a runtime authorization platform tailored for developers and security teams creating AI agents that interact with tools or APIs. Prior to executing a tool, the agent transmits action metadata—which encompasses details about the agent, the action being taken, the resource involved, the destination, and the count of records—and subsequently receives a decision categorized as ALLOW, REVIEW, or BLOCK, accompanied by a risk score ranging from 0 to 100 along with justifications. Teams have the flexibility to define and test YAML policies via a command-line interface, while also incorporating checks through Node.js or Python SDKs, a REST API, or various adapters compatible with agent frameworks. Additionally, the monitor mode enables the logging of decisions without hindering actions, and in the event that Vulnify becomes unavailable, a fail-closed protocol will prevent actions unless a fail-open setting is established. An audit log that utilizes hash chaining maintains a record of decisions made, with paid subscriptions offering the inclusion of human review processes. Typical applications of Vulnify include overseeing data exports, managing external communications, processing payments, and other actions initiated by agents. It is important to note that Vulnify focuses on evaluating action metadata instead of the actual contents of the records affected, ensuring a streamlined approach to authorization. Overall, this unique system helps enhance security and compliance for AI-driven operations.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Model Context Protocol (MCP)
Yes
CrewAI
No
GitHub
No
Jira
No
LangChain
No
LangGraph
No
OpenAI Agents SDK
No
Slack
No
Vercel AI SDK
No
Integrations
Model Context Protocol (MCP)
Yes
CrewAI
Yes
GitHub
Yes
Jira
Yes
LangChain
Yes
LangGraph
Yes
OpenAI Agents SDK
Yes
Slack
Yes
Vercel AI SDK
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
Free plan available
Developer: $0/month for 2 agents, 10,000 evaluated events/month, and 7-day event history; no review queue. Team: $99/month for 10 agents and 250,000 events/month. Business: $499/month for 50 agents and 2,000,000 events/month. Prices are in USD, excluding taxes. No annual plan or overage charge. Enterprise pricing and limits are by contract.
Free Trial
No
Free Version
Yes
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
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
No
Webinars
No
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
Vulnify
Country
Brazil
Website
www.vulnify.io