Go toolkit + library: structured adversarial corpora for LLM/RAG safety + quality testing. Prompt injection, KB exfiltration, jailbreak, system-prompt probing. CI/CD-ready.

Open-source LLM red teaming framework. Security-test any model (Claude, GPT, Llama) for prompt injection, data leakage, etc. 15 probes, 29 prompt converters, LLM-as-judge grading, adaptive red teaming, static code audit. SARIF + JUnit for CI/CD.

Adversarial Cognitive Portal Trap Architecture — A multi-layered defensive system that contains, degrades, disrupts, and commandeers autonomous offensive AI agents via a reverse kill chain (L0-L4).

Defensive AI infrastructure using differential topology to absorb attack variety. Building antifragile security systems.

Provide a Python-native framework to test and audit security in large language models with coverage of key OWASP LLM risks.