Open-source toolkit for adding programmable safety guardrails to LLM-powered applications using the Colang specification language for topic control, content filtering, and fact-checking.
Safety rails for AI applications — prevent your AI from going off-topic, generating harmful content, or exposing sensitive information using NVIDIA's programmable guardrail toolkit.
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable safety and control mechanisms to LLM-powered conversational systems. It addresses the critical challenge of keeping AI applications on-topic, safe, and compliant without requiring deep ML expertise.
The toolkit uses Colang, a custom specification language designed specifically for defining conversational guardrails. Colang 2.0 (the current version) provides an event-driven programming model where developers define flows that describe how the system should behave in various scenarios — what topics to avoid, how to handle sensitive requests, when to escalate to humans, and what factual claims to verify.
NeMo Guardrails operates through a multi-layered protection system. Input rails filter incoming user messages before they reach the LLM, checking for jailbreak attempts, off-topic requests, and policy violations. Output rails filter LLM responses before they reach the user, catching hallucinations, inappropriate content, and policy-violating statements. Dialog rails control the conversation flow itself, steering interactions away from prohibited topics.
The toolkit integrates with major LLM frameworks including LangChain, LangGraph, and LlamaIndex, and supports multi-agent deployments. It can leverage GPU acceleration for low-latency performance in production environments. Recent releases have added streaming support with proper word spacing, improved token counting accuracy, and integration with the GuardrailsAI validation ecosystem.
For enterprises deploying conversational AI in customer-facing roles, NeMo Guardrails provides the safety infrastructure needed to maintain trust and regulatory compliance. The Apache 2.0 license makes it accessible for commercial use, while NVIDIA's enterprise support option provides SLA guarantees for production deployments.
Was this helpful?
NeMo Guardrails is NVIDIA's open-source toolkit for adding programmable safety controls to LLM applications. Its Colang specification language makes writing safety rules accessible without ML expertise, while multi-layered input/output/dialog rails provide defense-in-depth. Best for enterprises deploying conversational AI in regulated or customer-facing environments.
An event-driven programming language specifically designed for defining conversational guardrails. Define flows, patterns, and rules that control how the AI system handles various scenarios without requiring ML expertise.
Use Case:
Writing a set of Colang flows that prevent a customer service bot from discussing competitor products, sharing internal pricing strategies, or making promises about delivery timelines.
Input rails filter user messages before LLM processing, output rails filter responses before delivery, and dialog rails control conversation flow. Each layer can be configured independently for defense-in-depth.
Use Case:
Configuring input rails to block jailbreak attempts, dialog rails to keep conversations on-topic, and output rails to catch hallucinated facts before they reach users.
Built-in mechanisms to verify LLM claims against provided knowledge bases, reducing hallucination in responses by cross-referencing generated content with authoritative sources.
Use Case:
A healthcare chatbot verifying that any medical information it provides aligns with the approved knowledge base before presenting it to patients.
Pre-built input rails that detect and block common jailbreak and prompt injection attempts, including role-play attacks, instruction override attempts, and social engineering patterns.
Use Case:
Protecting a public-facing chatbot from users attempting to manipulate the AI into ignoring its safety instructions or revealing system prompts.
Integrates with LangChain, LangGraph, LlamaIndex, and other frameworks. Can be added to existing LLM applications without rewriting core logic — guardrails wrap existing conversation flows.
Use Case:
Adding topic control and safety filtering to an existing LangChain-based customer support agent by wrapping it with NeMo Guardrails configuration.
Supports streaming LLM responses while still applying output rails, with proper word spacing and accurate token counting in streaming mode.
Use Case:
Deploying a real-time conversational agent that streams responses to users while still catching and filtering inappropriate content before it appears.
Free
Contact for pricing
Ready to get started with NVIDIA NeMo Guardrails?
View Pricing Options →We believe in transparent reviews. Here's what NVIDIA NeMo Guardrails doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
Recent releases improved streaming support with proper word spacing and accurate token counting, added GuardrailsAI integration for validator aliasing, expanded multi-agent deployment support, and introduced GPU-accelerated rail evaluation for low-latency production deployments.
No reviews yet. Be the first to share your experience!
Get started with NVIDIA NeMo Guardrails and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →