AIGoat - Open-source AI security playground for LLM red teaming. AI Goat provides hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.

Research-grade evaluation & verification platform for LLM agents, RAG pipelines, and tool-using workflows — grading tool-choice optimality, state-transition correctness, memory hygiene, privilege safety, recovery behavior, and multi-agent coordination beyond answer scoring.

PromptShield is an automated red-blue adversarial testing framework designed to evaluate LLM application security against prompt injection and data leakage, generating actionable mitigation reports mapped to the MITRE ATT&CK framework.