242  nemo-guardrails(1) - Kailash Tool Reference

242.1 nemo-guardrails

nemo-guardrails - NVIDIA NeMo Guardrails — programmable guardrails (topics, rails, jailbreak defence) for LLM conversational apps.

Layer DEFENCE
Category d-01-runtime-defence
Safety class safe
Licence Apache-2.0
Upstream github.com/NVIDIA-NeMo/Guardrails

242.1.1 NAME

nemo-guardrails - NVIDIA NeMo Guardrails — programmable guardrails (topics, rails, jailbreak defence) for LLM conversational apps.

242.1.2 SYNOPSIS & usage

Derived from the upstream README at generation time; verify against --help where the tool is installed.

> pip install nemoguardrails
from nemoguardrails import LLMRails, RailsConfig

# Load a guardrails configuration from the specified path.
config = RailsConfig.from_path("PATH/TO/CONFIG")
rails = LLMRails(config)

completion = rails.generate(
    messages=[{"role": "user", "content": "Hello world!"}]
)

242.1.3 DESCRIPTION (upstream)

LATEST RELEASE / DEVELOPMENT VERSION: The develop branch tracks the latest top of tree development. The latest released version is 0.24.1. ✨✨✨ 📌 The official NeMo Guardrails library documentation is available at docs.nvidia.com/nemo/guardrails. ✨✨✨ NVIDIA NeMo Guardrails library is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational applications. Guardrails (or “rails” for short) are specific ways of controlling the output of a large language model, such as not talking about politics

242.1.4 CONFIGURATION (detected)

Config-surface markers detected in the upstream README (16 matches, e.g. pr-tests.yml, pr-tests.yml). A full config reference page for this tool is queued under the config-page policy — this line is the detection record, not the page.

242.1.5 SEE ALSO

ref: pin - verified 2026-10-14