DOVER, Del.--(BUSINESS WIRE)--Apr 16, 2025--
SplxAI, the leader in offensive security for agentic AI, today announced enhancements to the SplxAI Platform with the addition of Agentic Radar, the company’s recently launched open-source project. The innovative open-source tool is the first to provide complete visibility into agentic AI workflows and their vulnerabilities, enabling CISOs and security teams to proactively mitigate AI risks and meet compliance requirements. SplxAI will be hosting 1:1 meetings at the RSA Conference to showcase this new capability.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20250416734068/en/
Agentic Radar maps the dependencies in agentic AI workflows and components using static code analysis to expose missing security measures within them. Designed to help security teams and AI engineers understand how their AI agents interact with tools, external components, and each other, Agentic Radar enables enterprises to proactively secure their agentic AI systems before they can be exploited. With the addition of Agentic Radar, SplxAI’s Platform now secures the full lifecycle of agentic AI, from development to deployment.
“Agentic Radar started as an open-source initiative to provide the broader security community with a foundational problem-solving tool for agentic AI workflow transparency and security,” said Kristian Kamber, CEO & Co-founder, SplxAI. “Agentic systems have complex workflows and often interact with multiple tools, making transparency and security assessment challenging. This tool simplifies the process by offering a structured view of workflows, tools, and potential risks. We saw immediate traction and success with the open-source project and received 405 stars on GitHub. This project has provided incredibly valuable feedback from developers, researchers and security professionals as we’ve moved toward incorporating the tool in SplxAI’s continuous automated red teaming platform for agentic AI.”
Agentic Radar will be embedded within the SplxAI Platform, the most comprehensive platform for offensive AI security, continuously adapting to secure even the most sophisticated multi-agent systems used throughout enterprise environments. The new tool offers a suite of powerful features that improve transparency and security in agentic AI systems.
The Agentic Radar Open-Source Project supports the leading frameworks for developing agentic workflows, including OpenAI Agents SDK, CrewAI, LangGraph and n8n, with more available soon.
The launch of the enhanced SplxAI Platform follows the close of the company’s $7 million seed funding round, which it is using to accelerate the development and adoption of the industry’s only continuous automated red teaming platform for agentic AI. Agentic Radar will be available within SplxAI’s Platform in 30 days.
About SplxAI
SplxAI is the most comprehensive platform for offensive AI security, continuously adapting to secure even the most sophisticated multi-agent systems used throughout enterprise environments. Founded in 2023, many large enterprises rely on SplxAI’s automated, scalable solution to detect, triage, and manage risks to their business-critical AI agents in real-time, enabling them to deploy AI at scale without introducing new vulnerabilities. To learn more, visit us at splx.ai.
After identifying all external tools, APIs, and services integrated into agentic AI workflows, Agentic Radar provides a visual graph that illustrates how these components interact within the system. Agentic Radar also detects and lists all MCP servers used by the system's agents. It then detects potential vulnerabilities in agentic AI workflows and maps them to leading AI security frameworks like OWASP Top 10 for LLM Applications and OWASP Agentic AI Threats and Mitigations Guide. Finally, Agentic Radar delivers clear and actionable recommendations to mitigate risks and strengthen the security of agentic AI systems. The results of Agentic Radar's workflow assessments are delivered in an HTML report for easy access and distribution.
