Agentic Radar

What is Agentic Radar?

Agentic Radar is an open-source security scanner for agentic AI systems, released by the SplxAI team, now part of SPLX and Zscaler. It reads the source code of an agent-based application with static analysis, then draws a graph of the agents, tools and external services in the workflow so you can see how decisions flow. It lists the tools and dependencies it finds, flags potential vulnerabilities and maps them to the OWASP Top 10 for LLM Applications and the OWASP Agentic AI threats guide, and offers remediation steps. Results come as an HTML report that is easy to share, and the output can feed more targeted gray-box red-teaming. SPLX shows examples with Microsoft AutoGen, the OpenAI Agents SDK, n8n and CrewAI, and says more frameworks are being added. The scanner itself is free; the same idea is extended into the paid SPLX platform, whose Professional and Enterprise plans are quoted on request.

Use cases

• Map the agents and tools in an AI workflow
• Scan agent code for security vulnerabilities
• Map risks to OWASP LLM Top 10
• Build an AI bill of materials
• Prepare targeted red-team assessments
• Share an HTML security report with reviewers

Who it's for

• Security engineers
• AI developers
• Red teamers
• Compliance teams

Why use Agentic Radar

• It shows how agents, tools and data flows connect, which black-box testing cannot reveal.
• Findings are tied to OWASP frameworks, making them easier to use in compliance discussions.
• Each finding comes with a description and remediation steps rather than just a flag.
• It is free and open source, so teams can try it on their own agent code without a sales call.
• The scan output can guide narrower, gray-box red-teaming of the same system.

Agentic Radar features

• Static source-code analysis of agentic workflows
• Graph of agents, tools and their connections
• Detection of external and custom tools
• Vulnerability mapping to the OWASP Top 10 for LLM Applications
• Mapping to the OWASP Agentic AI threats guide
• CVE findings from SBOM analysis
• Actionable remediation steps
• Shareable HTML report
• Examples for AutoGen, OpenAI Agents SDK, n8n and CrewAI

Agentic Radar integrations

• Microsoft AutoGen
• OpenAI Agents SDK
• n8n
• CrewAI
• MCP

How to get started with Agentic Radar

1. Install Agentic Radar from the public repository and point it at the source code of your agentic application.
2. It analyses the code statically to find agents, tools, MCP servers and how they connect.
3. It builds a workflow graph and lists the tools and dependencies it detects.
4. It maps potential vulnerabilities to OWASP LLM and agentic frameworks and attaches remediation steps.
5. Review the HTML report, share it with your team, and use it to plan deeper red-team tests.

Agentic Radar limitations

• Static analysis of source code, so it does not test a running system
• Supported frameworks are a growing list, and some entries are marked coming soon
• The commercial SPLX platform plans have no published prices

Agentic Radar pricing

Agentic Radar is open source, so you can use and self-host it for free.

Agentic Radar plans

• Professional

  Custom

  Get a Quote (SPLX platform)

  • 2000 credits a month
  • All probes and custom probes
  • Multi-modal support
  • Remediation steps
  • 99.9% uptime SLA

• Enterprise

  Custom

  Get a Quote (SPLX platform)

  • Compliance framework checks
  • Continuous threat monitoring
  • On-prem and hybrid deployment
  • SSO and SAML
  • Premium support

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

Agentic Radar alternatives

The main Agentic Radar alternatives listed on Debuly are Promptfoo, Agentic Security, Prediction Guard, smolagents, Letta and Agent Development Kit (ADK). The table compares pricing and platforms; order is A–Z.

1. 

   Agent Development Kit (ADK)

   Google's open-source, code-first Python framework for building, testing and deploying AI agents and multi-agent workflows.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit Agent Development Kit (ADK) (official site)
2. 

   Agentic Security

   Open-source vulnerability scanner that fuzzes and attacks LLM endpoints and agent workflows, from a pip install or CI check.

   Developer platformsCoding
   Open sourceVisit Agentic Security (official site)
3. 

   Letta

   Platform, formerly MemGPT, for building stateful AI agents with persistent memory, from a terminal app, SDK or API.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Letta (official site)
4. 

   Prediction Guard

   Self-hosted control plane that governs AI agent actions with runtime controls, a supply chain registry and audit logs.

   Developer platformsAutomation and agents
   Contact salesVisit Prediction Guard (official site)
5. 

   Promptfoo

   Open-source LLM evaluation and red-teaming tool that finds prompt injections, jailbreaks and data leaks in AI apps and agents.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Promptfoo (official site)
6. 

   smolagents

   Hugging Face's minimal open-source Python library for building agents that write their actions as code.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit smolagents (official site)

Agentic Radar FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from framerusercontent.com · fetched 23 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.