switchboard
N

NeMo Guardrails

by NVIDIA

Adds programmable guardrails to LLM apps — input/output moderation, jailbreak and prompt-injection detection, topic control, and fact-checking. Open-source Python toolkit by NVIDIA.

3
Skills
None
Auth
No
Streaming
No
Push

Skills

Jailbreak Detection

Detects jailbreak and prompt-injection attempts before they reach the underlying LLM.

Input/Output Moderation

Screens user inputs and model outputs against safety and content policies in real time.

Topic Rails

Constrains conversations to allowed topics and adds fact-checking rails to reduce hallucination.

Securityguardrailsllm-safetyjailbreak-detectionprompt-injectionmoderationopen-sourcenvidia
Visit Agent

Related Agents

O

OpenSandbox

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…

Infrastructure & OpsCode & DevTools
APIMCPCLI
5 skillsAPI Key
N

NVIDIA SkillSpector

Featured

Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…

SecurityCode & DevTools
CLI
4 skillsNone
A

Archestra

Run MCP servers for an enterprise behind one gateway — a curated registry, dynamic tool loading, prompt-injection guard…

Infrastructure & OpsSecurity
MCPAPI
3 skillsOAuth 2.0
p

promptfoo

Tests and red-teams LLM apps, agents and RAG pipelines from declarative config, scanning for prompt injection, jailbrea…

SecurityCode & DevTools
CLIAPI
3 skillsNone
nemo-guardrails
Adds programmable guardrails to LLM apps — input/output moderation, jailbreak and prompt-injection detection, topic control, and fact-checking. Open-source Python toolkit by NVIDIA.
fields
nameNeMo Guardrails
providerNVIDIA
urlhttps://github.com/NVIDIA-NeMo/Guardrails
categoriessecurity
accessapi
authnone
streamingfalse
pushfalse
verifiedtrue
tagsguardrails, llm-safety, jailbreak-detection, prompt-injection, moderation, open-source, nvidia
skills
jailbreak-detectionJailbreak DetectionDetects jailbreak and prompt-injection attempts before …
io-moderationInput/Output ModerationScreens user inputs and model outputs against safety an…
topic-railsTopic RailsConstrains conversations to allowed topics and adds fac…
→ https://github.com/NVIDIA-NeMo/Guardrails