nemo-guardrails
from Orchestra-Research/AI-research-SKILLs
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.
v1.0.0MIT
298
Lines
893
Words
10
Code Blocks
Languages
bashpython
07-safety-alignment/nemo-guardrails/SKILL.md