An open-source enterprise-grade AI guardrails, supporting both security gateway mode and API-based detection. It provides protection against prompt injection attacks, content safety risks and data leakage. Built on LLM with contextual awareness, it also supports fully private deployment.

A Python implementation of the VETTING (Verification and Evaluation Tool for Targeting Invalid Narrative Generation) framework for LLM safety and educational applications.

A secure, governable AI gateway for Splunk with operational guardrails. An alternative to Splunk AI Assistant focused on safety, compliance, and predictable results using a 'Configuration as Code' approach."

DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems