
ironclaw
Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

A collection of Azure AD/Entra tools for offensive and defensive security purposes

An open-source framework for verifiably private AI inference

MAAD Attack Framework - An attack tool for simple, fast & effective security testing of M365 & Entra ID (Azure AD).


credential isolation for AI agents. Agents never see real API keys - structural guarantee, not policy.

Open-source framework for embedding realistic decoy routes and honey fields into APIs to detect attackers probing business logic, converting…

A attempt at cryptographic framework for Baochip-1x .