Every tool we ship was born from a real engagement — then open-sourced when it stopped being proprietary advantage and started being table stakes.

Intentionally vulnerable LLM fine-tuned on Falcon 7B for red team training and AI security research.

Node.js security library with 9 named security layers, 22 connector packages, and 60+ tests in core for protecting LLM applications from prompt injection to data leakage.

LLM security testing platform with 540+ attack patterns across 49 groups, 15 user-facing modules, 28 detector modules, and 60+ LLM provider presets. Coming soon.

Hardened LLM fine-tuned for security research: the defensive counterpart to Basileak.

Production-ready multi-agent operations framework with 40+ public agents across 3 specialised teams (Cybersec / Intel / Strategy), 250+ workflows, 350+ slash commands, and OWASP LLM 95/100.

BUCC is the production multi-agent operations platform we built to run our own 30+ agent fleet. Not a product we sell. The open hood on how we engineer a secure agentic framework.