# Adversa AI

> Continuous AI red teaming and runtime security for AI coding agents, LLMs, GenAI, agentic AI, and MCP systems — helping enterprises in financial services, insurance, and government find and fix AI-specific vulnerabilities before attackers do.

Adversa AI runs adversarial testing and runtime protection across the AI lifecycle — awareness, assessment, and assurance — mapped to frameworks including OWASP, MITRE ATLAS, NIST AI RMF, and the EU AI Act.

## Platform

- [AI red teaming for agentic AI](https://adversa.ai/ai-red-teaming-agentic-ai/): continuous red teaming for AI agents, LLMs, GenAI, and MCP systems.
- [Runtime security platform](https://adversa.ai/runtime-security-platform/): runtime protection for AI coding agents.

## Research and resources

- [Trusted AI Blog](https://adversa.ai/blog/): research, red teaming insights, and AI security news.
- [Resource center](https://adversa.ai/resources/): reports and whitepapers on securing GenAI and agentic AI.
- [RSS feed](https://adversa.ai/rss.xml): the latest posts.

## Company

- [About Adversa AI](https://adversa.ai/about-us/): the team and mission.
- [Security and trust](https://adversa.ai/security-trust/): our security posture.

## Compliance

- [EU AI Act compliance](https://adversa.ai/compliance/eu-ai-act/)
- [Digital Services Act (DSA) compliance](https://adversa.ai/compliance/dsa/)
- [Digital Markets Act (DMA) compliance](https://adversa.ai/compliance/dma/)