AI Security Landscape – Solutions Directory

The landscape directory includes traditional and emerging security controls addressing Generative
AI, Agentic and AI Red Teaming. It is not a comprehensive list or an endorsement but a community
resource of open source and proprietary solutions.

Simple Sort
LLMTop10 2025
LLMTop10 2023
Agetntic T10
Red Team Categories

Landscape

Landscape
  • GenAI LLM (145)
  • Agentic (83)
  • Red Teaming (38)

Solution Type

Solution Type
  • Commercial (230)
  • Open Source (38)
  • Proprietary (3)

SecOps Stages

SecOps Stages
  • Test & Evaluate (106)
  • Monitor (89)
  • Operate (82)
  • Govern (71)
  • Deploy (56)
  • Develop & Experiment (51)
  • Scope & Plan (42)
  • Augm & Fine Tune Data (26)
  • Release (22)
  • Test & Evaluation (1)
Company, OSS Project:
Fujitsu Limited
Wiz
Commercial
GenAI LLM
Solution:

Fujitsu GenAI Security Framework (LLM Vulnerability Scanner and Guardrails)

Secure your GenAI systems with our industry-leading LLM Vulnerability Scanner and Guardrails Ñ enabling automated defense against 7,800+ attacks and empowering even non-experts to safely operate generative AI with confidence.
Secure your GenAI systems with our industry-leading LLM Vulnerability Scanner and Guardrails Ñ enabling automated defense against 7,800+ attacks and empowering even non-experts to safely operate generative AI with confidence.
Company, OSS Project:
Enkrypt AI
Wiz
Commercial
GenAI LLM
Solution:

Enkrypt AI

Enkrypt AI secures enterprises against generative AI risks with its comprehensive security platform that detects threats, removes vulnerabilities, and monitors the latest insights on security, compliance and AI performance.
Enkrypt AI secures enterprises against generative AI risks with its comprehensive security platform that detects threats, removes vulnerabilities, and monitors the latest insights on security, compliance and AI performance.
Company, OSS Project:
Fujitsu
Wiz
Commercial
Red Teaming
Solution:

Fujitsu Agentic AI Scanner

Fujitsu Agentic AI Scanning closes the gaps in agentic AI security by introducing a unified scanning pipeline that reconstructs, simulates, and stress-tests agentic systems in a safe, controlled environment.
Fujitsu Agentic AI Scanning closes the gaps in agentic AI security by introducing a unified scanning pipeline that reconstructs, simulates, and stress-tests agentic systems in a safe, controlled environment.
Company, OSS Project:
ActiveFence
Wiz
Commercial
Solution:

ActiveFence | Red Teaming

ActiveFence Guardrails monitors generative AI inputs and outputs in real-time. It enforces customizable policies across text, image, audio, and video, providing live visibility and intervening to prevent unsafe or misaligned
ActiveFence Guardrails monitors generative AI inputs and outputs in real-time. It enforces customizable policies across text, image, audio, and video, providing live visibility and intervening to prevent unsafe or misaligned behaviors with contextualized localization in 20+ languages.
Company, OSS Project:
Radware
Wiz
Commercial
Agentic
Solution:

Radware Agentic AI Protection

Radware Agentic AI Protection provides real_time visibility, behavioral detection, and continuous posture monitoring to secure autonomous AI agents, detect misuse, and control interactions across tools, platforms, and environments.
Radware Agentic AI Protection provides real_time visibility, behavioral detection, and continuous posture monitoring to secure autonomous AI agents, detect misuse, and control interactions across tools, platforms, and environments.
Company, OSS Project:
Tenable AI
Wiz
Commercial
Agentic
Solution:

Tenable AI (Apex acquired by Tenable)

Tenable AI delivers preemptive, in-depth protection against adversarial threats, risky insiders and agents across all GenAI enterprise applications, including ChatGPT Enterprise, Microsoft Copilot, and internally built GenAI based applications.
Tenable AI delivers preemptive, in-depth protection against adversarial threats, risky insiders and agents across all GenAI enterprise applications, including ChatGPT Enterprise, Microsoft Copilot, and internally built GenAI based applications.
Company, OSS Project:
ForceAI Security
Wiz
Commercial
GenAI LLM
Solution:

ForceAI SPM

AI-SPM secures AI systems through design-time hardening and run-time enforcement, continuously monitoring models, data, prompts, and infrastructure to reduce risk, strengthen governance, and maintain trustworthy AI operations.
AI-SPM secures AI systems through design-time hardening and run-time enforcement, continuously monitoring models, data, prompts, and infrastructure to reduce risk, strengthen governance, and maintain trustworthy AI operations.
Company, OSS Project:
Spellguard.ai
Wiz
Commercial
Agentic
Solution:

Spellguard.ai

Spellguard is a security platform for AI agents that routes all messages and tool calls through a Trusted Execution Environment for real-time policy enforcement, encrypted messaging, and tamper-proof audit logging.
Spellguard is a security platform for AI agents that routes all messages and tool calls through a Trusted Execution Environment for real-time policy enforcement, encrypted messaging, and tamper-proof audit logging.
Company, OSS Project:
Apex Security AI
Wiz
Commercial
GenAI LLM
Solution:

Apex Security AI

Apex Security leverages proprietary AI models to detect adversarial attempts in LLM inputs/outputs, identifying sensitive data exposure, leakage, complex manipulations, and risky agents. It integrates seamlessly and agentlessly with enterprise
Apex Security leverages proprietary AI models to detect adversarial attempts in LLM inputs/outputs, identifying sensitive data exposure, leakage, complex manipulations, and risky agents. It integrates seamlessly and agentlessly with enterprise Generative AI platforms.
Company, OSS Project:
HiddenLayer
Wiz
Commercial
Red Teaming
Solution:

HiddenLayer AI Security Platform

Our platform proactively defends against the full spectrum of AI threats, safeguarding your IP, compliance posture, and enterprise operations.HiddenLayer AI Security Platform

Company, OSS Project:
IBM
Wiz
Commercial
Agentic
Solution:

IBM Guardium AI Security

IBM Guardium AI Security allows organizations to discover shadow AI, secure all AI models and use cases, get real-time protection from malicious prompts, and align teams on common set of
IBM Guardium AI Security allows organizations to discover shadow AI, secure all AI models and use cases, get real-time protection from malicious prompts, and align teams on common set of metrics—for secure and trustworthy AI.
Company, OSS Project:
Pangea
Wiz
Commercial
GenAI LLM
Solution:

Pangea Data Guard

Prompt inputs, responses, and data ingestion from external sources can all be evaluated for malicious content with Pangea's Data Guard to protect LLMs and users from threatening content.
Prompt inputs, responses, and data ingestion from external sources can all be evaluated for malicious content with Pangea's Data Guard to protect LLMs and users from threatening content.
Company, OSS Project:
Citadel AI
Wiz
Commercial
GenAI LLM
Solution:

Citadel Lens

Citadel Lens is a tool for multilingual, automated red teaming and evaluation of LLM applications.
Citadel Lens is a tool for multilingual, automated red teaming and evaluation of LLM applications.
Company, OSS Project:
CalypsoAI
Wiz
Commercial
GenAI LLM
Solution:

The CalypsoAI Inference Platform

CalypsoAI secures GenAI across applications and agents. The CalypsoAI Inference Platform tests, defends, and monitors AI in development and production. With Defend, Red-Team, and Observe, enterprises gain control and confidence
CalypsoAI secures GenAI across applications and agents. The CalypsoAI Inference Platform tests, defends, and monitors AI in development and production. With Defend, Red-Team, and Observe, enterprises gain control and confidence in their GenAI deployments.
Company, OSS Project:
Preamble
Wiz
Commercial
GenAI LLM
Solution:

AI Trust Platform

Preamble provides runtime guardrails for RAG, LLMs, and AI agents by enforcing safety, privacy, security, and compliance policies while mitigating real-time risks to ensure secure, reliable AI operations.
Preamble provides runtime guardrails for RAG, LLMs, and AI agents by enforcing safety, privacy, security, and compliance policies while mitigating real-time risks to ensure secure, reliable AI operations.
Company, OSS Project:
EUNOMATIX
Wiz
Commercial
GenAI LLM
Solution:

LLMInspect

LLMInspect is an enterprise-level Generative AI Gateway to detect and block data leakages and data threats while ensuring the safe use of Commercial LLMs (like OpenAI, Gemini, DeepSeek, Mistral, etc).
LLMInspect is an enterprise-level Generative AI Gateway to detect and block data leakages and data threats while ensuring the safe use of Commercial LLMs (like OpenAI, Gemini, DeepSeek, Mistral, etc).
Company, OSS Project:
Aim Security
Wiz
Commercial
GenAI LLM
Solution:

Aim Security

The Aim AI Security platform ensures the security of every AI interaction, agent, and application, safeguarding against adversarial attacks, data leaks, and compliance breaches.
The Aim AI Security platform ensures the security of every AI interaction, agent, and application, safeguarding against adversarial attacks, data leaks, and compliance breaches.
Company, OSS Project:
Pomerium
Wiz
Open Source
GenAI LLM
Solution:

Pomerium

Pomerium adds per request authentication and authorization with verbose logging for AI Agents and LLMs accessing MCP Servers.
Pomerium adds per request authentication and authorization with verbose logging for AI Agents and LLMs accessing MCP Servers.
Company, OSS Project:
Meta
Wiz
Open Source
GenAI LLM
Solution:

Llama Guard

Llama Guard is a set of LLM system safeguards designed to support developers to detect various common types of violating content across multiple use cases including multilingual, image reasoning, or
Llama Guard is a set of LLM system safeguards designed to support developers to detect various common types of violating content across multiple use cases including multilingual, image reasoning, or on-device deployments.
Company, OSS Project:
(Not Provided)
Wiz
Commercial
Agentic
Solution:

TrojAI

TrojAI helps secure AI models, applications, and agents across both AI build time and AI runtime

Visit Solution
Company, OSS Project:
Mend AI
Wiz
Commercial
GenAI LLM
Solution:

Mend AI

Mend AI provides a shift-left solution for securing AI-driven applications. It enables discovery of shadow AI, security and compliance analysis through code scanning and red-teaming, and remediation with guardrails and
Mend AI provides a shift-left solution for securing AI-driven applications. It enables discovery of shadow AI, security and compliance analysis through code scanning and red-teaming, and remediation with guardrails and fix suggestions.
Scroll to Top

Solutions Directory