Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/Guardrails
Library/GuardrailsForked

NVIDIA-NeMo/Guardrails

Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

View on GitHub↗Upstream NVIDIA-NeMo/Guardrails↗

Builder

NVIDIA-NeMo

NVIDIA-NeMo

NVIDIA-NeMo • individual

Stars

5,854

Using upstream star count

Forks

635

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Apr 18, 2023

Project creation date

README Summary

NeMo Guardrails is an open-source toolkit developed by NVIDIA for adding programmable safety guardrails to large language model (LLM) based conversational systems. The toolkit provides developers with tools to implement content filtering, response validation, and behavioral constraints to ensure AI conversations remain safe, appropriate, and aligned with intended use cases. It offers a flexible framework for defining custom rules and policies that can be applied to various LLM applications.

Community Evaluation

Loading…

AI Dev Skills

Unmapped

AI Content FilteringAI Safety and AlignmentConversational AI SystemsConversational Flow ControlDialogue ManagementLarge Language Model IntegrationLLM Prompt EngineeringRule-based AI Control Systems

Tags

AI Content FilteringAI Safety and AlignmentConversational AI SystemsConversational Flow ControlDialogue ManagementLarge Language Model IntegrationLLM Prompt EngineeringRule-based AI Control SystemsContent Moderation for AI AssistantsInappropriate Response PreventionAI AlignmentSelf-hostedTextCloud APILLM GovernanceAI SafetyOn-premiseEnterprise SoftwareConversational Flow ManagementCompliance-driven Conversational AILegal TechCustomer ServiceTopic Boundary EnforcementFinTechChatbot Safety ControlConversational AIEnterprise AI Assistant GovernanceHealthcareEducationResponsible AIPython

Taxonomy

AI Trends

AI SafetyResponsible AILLM GovernanceConversational AIAI Alignment

Deployment Context

Self-hostedCloud APIOn-premise

Industries

Customer ServiceHealthcareFinTechLegal TechEducationEnterprise Software

Modalities

Text

Skill Areas

Large Language Model IntegrationConversational AI SystemsAI Safety and AlignmentRule-based AI Control SystemsLLM Prompt EngineeringDialogue ManagementAI Content FilteringConversational Flow Control

Use Cases

Chatbot Safety ControlContent Moderation for AI AssistantsCompliance-driven Conversational AITopic Boundary EnforcementInappropriate Response PreventionConversational Flow ManagementEnterprise AI Assistant Governance

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

beta
Quality
high
Maturity
beta

Categories

Evals & BenchmarkingPrimaryDev Tools & AutomationIndustry: FinTechSafety & AlignmentHealthcare & BiologyFinance & LegalOther AI / MLFoundation ModelsAI AgentsRobotics

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Apr 18, 2023
Forked
Mar 13, 2026
Your last push
2 months ago
Upstream last push
1 months ago
Tracked since
Mar 13, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…