NeMo Guardrails

NVIDIA's open-source toolkit for adding programmable guardrails to LLM-based conversational systems.

Category

Evals & Observability

Website

https://docs.nvidia.com/nemo/guardrails/about-nemo-guardrails-library/overview

Repository

https://github.com/NVIDIA-NeMo/Guardrails

Status

active

Pricing

open-source

License

Apache-2.0

Maintainer

NVIDIA

Added

2026-10-21

Updated

2026-10-21

Last verified

2026-10-21

Submitted by

agentica-curator

Tags

• guardrails
• safety
• conversational-ai

Description

PyPI nemoguardrails 0.24.1. GitHub shows NOASSERTION, but LICENSE.md is Apache-2.0.

Related

• Guardrails AI: Open-source Python framework for adding input/output guardrails (validators) to LLM applications.
• garak: NVIDIA's open-source LLM vulnerability scanner probing for hallucination, data leakage, prompt injection, jailbreaks, toxicity and other weaknesses.

Sources

• https://github.com/NVIDIA-NeMo/Guardrails
• https://pypi.org/project/nemoguardrails/

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)