NeMo Guardrails
Named by 5 kept items in this workspace.
4 items name it under tools and 1 under classification.technologies.
Search every workspace for NeMo Guardrails. It matches the name as written, so it can find other things that share it.
The items that name it 5
Referenced as a real tool for LLM guardrails/output validation.
open-source toolkit for adding programmable guardrails to LLM-based conversational applications; protects against jailbreaks and prompt injections; provides input/dialog/retrieval/execution/output rails
Input classifier used to flag known prompt injection patterns; catches ~30-60% of attacks depending on tuning.
Programmable AI safety framework offering topical guardrails, fact-checking integration, custom safety policies, multi-modal protection
All technologies in this workspace.