ai-supply-chain
Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.
Python security gates for LLM systems: prompt-injection filtering, model artifact scanning, and garak-based red-team scoring.
Offline-first evidence and verification framework for AI model artifacts, transformations, runtime identity, and provenance.
