NVIDIA-NeMo/Guardrails
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Builder
NVIDIA-NeMo
NVIDIA-NeMo • individual
Stars
6,298
Using upstream star count
Forks
702
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Apr 18, 2023
Project creation date
README Summary
[](https://opensource.org/licenses/Apache-2.0) [](https://pypi.org/project/nemoguardrails) [](https://pypi.org/project/nemoguardrails) [](https://github.com/NVIDIA
Community Evaluation
Loading…AI Dev Skills
Unmapped
AI Guardrails ImplementationAI Safety EngineeringContent FilteringContent ModerationContent Moderation and FilteringConversational AIConversational AI ArchitectureConversational AI SystemsCustom LLM OrchestrationDialog Flow ManagementDialogue Flow ControlDialogue ManagementGuardrail Design PatternsIntent RecognitionLarge Language Model SafetyLLM AlignmentLLM IntegrationLLM Integration ArchitectureLLM Output FilteringLLM Output ValidationLLM Safety and AlignmentMulti-modal LLM HandlingMulti-model LLM IntegrationMulti-turn Conversation HandlingNatural Language UnderstandingPolicy-as-CodePolicy Enforcement in AI SystemsPrompt EngineeringRisk Mitigation for Language ModelsRule-based AI Control SystemsRuntime Constraint EnforcementToxicity Detection
Tags
AI Guardrails ImplementationAI Safety EngineeringContent FilteringContent ModerationContent Moderation and FilteringConversational AIConversational AI ArchitectureConversational AI SystemsCustom LLM OrchestrationDialog Flow ManagementDialogue Flow ControlDialogue ManagementGuardrail Design PatternsIntent RecognitionLarge Language Model SafetyLLM AlignmentLLM IntegrationLLM Integration ArchitectureLLM Output FilteringLLM Output ValidationLLM Safety and AlignmentMulti-modal LLM HandlingMulti-model LLM IntegrationMulti-turn Conversation HandlingNatural Language UnderstandingPolicy-as-CodePolicy Enforcement in AI SystemsPrompt EngineeringRisk Mitigation for Language ModelsRule-based AI Control SystemsRuntime Constraint EnforcementToxicity DetectionAPIC++DockerEvalsForkedGPTGuardrailsLangChainLarge Language ModelsNeMo GuardrailsNode.jsOpenAIPrompt InjectionPythonRAGResearch / PapersSecurityTutorial
Taxonomy
AI Trends
category
Deployment Context
Industries
Modalities
Skill Areas
Large Language Model SafetyPrompt EngineeringDialogue Flow ControlContent Moderation and FilteringConversational AI ArchitectureLLM Output ValidationPolicy Enforcement in AI SystemsNatural Language UnderstandingIntent RecognitionGuardrail Design PatternsMulti-model LLM IntegrationLLM Safety and AlignmentConversational AIPolicy-as-CodeContent FilteringToxicity DetectionDialog Flow ManagementLLM Integration ArchitectureRuntime Constraint EnforcementMulti-modal LLM HandlingConversational AI SystemsLLM Output FilteringContent ModerationDialogue ManagementLLM AlignmentRisk Mitigation for Language ModelsRule-based AI Control SystemsMulti-turn Conversation HandlingCustom LLM OrchestrationAI Guardrails ImplementationAI Safety EngineeringLLM Integration
tag
Use Cases
Safe LLM-powered chatbotsContent policy enforcementOff-topic prevention in conversational AIRegulatory compliance in automated dialogueBrand safety guardrailsHarmful content detection and preventionDialogue flow constraint enforcementMulti-turn conversation safetyContent Moderation for ChatbotsBrand Safety EnforcementCompliance-Aware Conversational AgentsHarmful Content PreventionBusiness Logic Enforcement in Dialog SystemsPolicy-Based LLM Output FilteringCustomer Service Bot SafeguardingAdding safety guardrails to chatbotsContent policy enforcement in conversational AIPreventing harmful model outputsDomain-specific conversation constraintsCompliance-aware LLM systemsBusiness logic enforcement in LLM applicationsTopic restriction in customer-facing chatbotsPreventing jailbreaks and adversarial promptsLLM Safety EnforcementConversational AI Content FilteringChatbot Behavior ControlAI Assistant SafetyLLM Response Validation
Recent Activity
Updated 2 months ago
7 Days
0
30 Days
0
90 Days
16
Quality
beta- Quality
- high
- Maturity
- beta
Categories
Dev Tools & AutomationPrimaryRAG & RetrievalEvals & BenchmarkingMLOps & InfrastructureLearning ResourcesSecurity & SafetyFoundation ModelsAI AgentsSafety & AlignmentSearch & KnowledgeOther AI / ML
PM Skills
Safety & AlignmentScale & ReliabilityData & EvaluationProduct DiscoveryDeveloper Platform
Languages
Python100.0%
Timeline
- Project created
- Apr 18, 2023
- Forked
- Mar 13, 2026
- Your last push
- 2 months ago
- Upstream last push
- 16 days ago
- Tracked since
- Mar 13, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…