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.
The CalypsoAI Inference Platform Read Post »
AiFort by KELA is an automated, intelligence-led red teaming platform designed to protect GenAI applications. AiFort allows organizations full protection through test simulations of their GenAI applications against a wide range of violation scenarios.
Secure AI Applications using two products. Ascend AI provides pentesting/red teaming across all layers of the applications. Defend AI provides visibility, guardrails for AI applications. With both approaches, we take a look at the threat vector at the application layer and not just the models
AIM Supervisor integrates AIM RED for automated AI vulnerability testing, AIM GUARD for real-time threat detection and mitigation, and AIM Benchmark for comprehensive safety evaluations, ensuring continuous, adaptive protection against evolving AI security threats.
The Infosys Responsible AI Toolkit (Technical Guardrail) is API Based solution designed to
ensure the ethical and responsible development of AI applications. By integrating safety, security, explainability, fairness, bias and hallucination detection into AI workflows, it empowers us to build trustworthy and accountable AI systems.
Infosys Responsible AI Toolkit Read Post »
TrojAI Detect secures AI behavior at build time. The AI security platform continuously red teams AI models to find security weaknesses in AI, ML, and GenAI models during model development before they can be exploited.
Vulcan is an LLM risk and vulnerability testing solution that enables AI project teams to perform automatic red teaming at scale.
LangCheck is a multilingual, Pythonic toolkit to evaluate LLM applications – use it to create unit tests, monitoring, guardrails, and more.
Citadel Lens is a tool for multilingual, automated red teaming and evaluation of LLM applications.
Recon runs automated and comprehensive penetration testing attacks on your LLM powered applications, to help protect you from unique security threats and vulnerabilities. It has the ability to run attacks from an attack library, use an agent for completely automated scans or perform human augmented scans using an LLM Agent.
warranty of service or accuracy. For more information, please refer to our General Disclaimer. – Copyright © 2025 OWASP Foundation, Inc.