NVIDIA NeMo Guardrails
VerifiedNVIDIA's open-source toolkit for adding programmable guardrails to LLM-based conversational systems. 6,500+ GitHub stars.
Frameworks Covered
NIST-AI-RMF
Services
llm-guardrailscontent-moderationjailbreak-protectionpii-maskingtopic-control
About NeMo Guardrails
NeMo Guardrails is an open-source toolkit by NVIDIA for easily adding programmable guardrails to LLM-based conversational applications. Guardrails control the output of LLMs — blocking off-topic content, preventing jailbreaks, masking PII, and following predefined dialog paths.
Features
- Content safety guardrails (input/output moderation)
- Jailbreak protection (self-check, heuristic detection, NVIDIA NemoGuard)
- Topic control (restrict conversations to allowed topics)
- PII detection and masking
- Dialog rails (predefined conversational flows via Colang)
- Integration with LlamaGuard, ActiveFence, Cisco AI Defense
- LangChain integration
Installation
pip install nemoguardrails
Loading reviews...