7 projects
sovereign-rag-gateway
Policy-first OpenAI-compatible gateway for regulated workloads
mmsafe-bench
Multi-modal AI safety evaluation framework for red-teaming generative models across text, image, video, and audio
ai-provenance-tracker
Detect AI-generated content, trace origins, verify authenticity
ogulcanaydogan-mcp-security-scanner
Security scanner for Model Context Protocol (MCP) servers. Detects prompt injection, tool poisoning, capability escalation, and rug-pull attacks.
eu-ai-act-compliance-kit
Automated EU AI Act (2024/1689) compliance checker. Classifies AI systems by risk tier, generates checklists, and produces audit-ready reports.
llm-behavior-diff
Behavioral regression testing tool for LLM model upgrades. Compare model versions and detect behavioral changes.
ai-regulation-scanner
Scan AI systems for EU/UK/NIST AI regulation compliance
