nemo-guardrails
// NVIDIA NeMo Guardrails configuration for conversational safety and control
$ git log --oneline --stat
stars:384
forks:73
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
namenemo-guardrails
descriptionNVIDIA NeMo Guardrails configuration for conversational safety and control
allowed-toolsRead,Write,Edit,Bash,Glob,Grep
NeMo Guardrails Skill
Capabilities
- Configure NeMo Guardrails rails
- Design Colang conversation flows
- Implement input/output rails
- Set up topic control
- Configure jailbreak detection
- Implement fact-checking rails
Target Processes
- system-prompt-guardrails
- content-moderation-safety
Implementation Details
Rail Types
- Input Rails: Filter user inputs
- Output Rails: Filter LLM outputs
- Dialog Rails: Control conversation flow
- Retrieval Rails: Filter retrieved content
- Execution Rails: Control action execution
Colang Components
- Flow definitions
- Bot message templates
- User message patterns
- Actions and subflows
Configuration Options
- Rails configuration
- LLM selection
- Embedding model
- Action handlers
- Custom rail implementations
Best Practices
- Start with built-in rails
- Design clear flows
- Test with adversarial inputs
- Monitor rail activations
Dependencies
- nemoguardrails