Purpose-built open-source tools covering every stage of AI security — from learning the attack surface to operating hardened, autonomous systems.
Learn · Defend · Test · Harden · Operate
Testing Lab
Platform tier
LLM security testing platform with 534 attack patterns across 47 groups, 15 core modules, 6 heuristic detectors, and 15+ LLM provider support.
Learn
Ecosystem tier
Intentionally vulnerable LLM fine-tuned on Falcon 7B for red team training and AI security research.
Defend
Ecosystem tier
Node.js security library with 8 security layers, 20+ connector packages, and 3,700+ tests for protecting LLM applications from prompt injection to data leakage.
Harden
Ecosystem tier
Hardened LLM fine-tuned for security research: the defensive counterpart to Basileak.
Operate
Framework tier
Production-ready multi-agent operations framework with 80+ agents, 201 workflows, 4 specialized teams, and 20+ compliance frameworks.