NVIDIA NeMo Guardrails

The NVIDIA NeMo Guardrails library is an open-source Python package for adding programmable guardrails to LLM-based applications. Use it to block, alter, or validate unsafe, off-topic, malicious, or policy-violating user inputs and model responses. The library provides configuration files, Colang flows, built-in guardrails, custom actions, and integration APIs so you can add safety and control logic without rewriting your application or model backend.

Official product page

4published use cases

2industries

3countries on record

Conversational AI

top AI capability

Evidence mix: High 4 · Medium 0 · Low 0 — bands are computed from each record's evidence signals.

Industry

Country

4 use cases

PharmaceuticalsGenerative AIPredictive AnalyticsComputer Vision

Roche scales NVIDIA AI factories globally to accelerate drug discovery, diagnostics and manufacturing

Roche is deploying more than 3,500 NVIDIA Blackwell GPUs across hybrid cloud and on-premises environments in the U.S. and Europe, expanding an existing collaboration to turn AI and accelerated computing into a core operating capability across its pharmaceutical and diagnostics businesses. AI is central to Genentech's Lab-in-the-Loop drug discovery strategy, where nearly 90% of eligible small-molecule programs integrate AI; in one program a degrader molecule for oncology was designed 25% faster, and in another AI helped deliver a backup drug candidate in seven months instead of more than two years. Roche is also using NVIDIA Omniverse to build digital twins of manufacturing sites, including its new GLP-1 facility in North Carolina, uses NVIDIA Parabricks software to enable insights across vast datasets, is evaluating the BioNeMo platform for molecular design and chemistry innovation, and uses NVIDIA NeMo Guardrails to ensure safe and reliable healthcare-grade AI.

RocheNVIDIA Blackwell · NVIDIA BioNeMo · NVIDIA Omniverse +2

PharmaceuticalsGenerative AIPredictive AnalyticsConversational AIComputer Vision

Roche launches NVIDIA AI factory to accelerate the development of new therapeutics and diagnostics solutions

Roche deployed 2,176 NVIDIA Blackwell GPUs on premises across the United States and Europe, bringing its combined on-premise and cloud GPU infrastructure to more than 3,500 Blackwell GPUs. The AI factory is embedded across the value chain: NVIDIA BioNeMo powers Roche's Lab-in-the-Loop strategy connecting biological and chemistry experiments with AI models in R&D; NVIDIA Omniverse-powered digital twins optimize manufacturing production lines and factory designs; accelerated computing and NVIDIA Parabricks analyze diagnostics datasets and digital pathology images; and NVIDIA NeMo Guardrails support healthcare-grade conversational AI in digital health. The expansion builds on a NVIDIA collaboration that started in 2023, and Roche's U.S. subsidiary Genentech also leverages the infrastructure for drug discovery.

Roche· SwitzerlandNVIDIA Blackwell · NVIDIA BioNeMo · NVIDIA Omniverse +2

Government & Public SectorRetrieval-Augmented GenerationNatural Language ProcessingConversational AI

WideLabs Justice Intelligence platform makes legal services more accessible for 8 million citizens in Rio Grande do Sul, Brazil

WideLabs built the Justice Intelligence platform for the Public Ministry of Rio Grande do Sul (MPRS) in Brazil, consisting of two AI agents — the TORI Investigation Assistant and the Archiving Intelligence Assistant — plus a Citizen Access Agent for the public. The platform uses NVIDIA NeMo Retriever for RAG pipelines, NVIDIA NIM microservices for deployment, NVIDIA NeMo Curator for document preprocessing, NVIDIA NeMo Customizer for domain-specific model tuning, and NVIDIA NeMo Guardrails for safety and consistency. The system went into full production in January 2025, serving more than 8 million citizens across 497 municipalities, and per MPRS deputy attorney general João Cláudio Pizzato Sidou, procedures that could last months or years can now be resolved or advanced in less than a day.

Public Ministry of Rio Grande do Sul (MPRS)· BrazilNVIDIA NeMo Retriever · NVIDIA NIM · NVIDIA NeMo Curator +3

Government & Public SectorDocument IntelligenceConversational AIGenerative AIAgentic AI

ThinkDeep's DeepBrain AI agents help automate public services for the French government

ThinkDeep AI developed DeepBrain, a multi-agent assistant platform for France's Ministry of Economy and Finance and Ministry of Defense, built on NVIDIA AI Enterprise (NIM, NeMo Retriever, NeMo Guardrails, Llama Nemotron models) running on-premises on NVIDIA DGX H100 systems to keep sensitive data within government infrastructure and comply with the EU AI Act. DeepBrain agents process millions of PDF documents, scanned images, schemas and videos for use cases including fraud detection and legal document processing. Document retrieval time fell from two days to two minutes, a typical 100-user deployment saves 1,000 work hours per month, and the Ministry of Finance has saved €2 million deploying DeepBrain at scale to 10,000 employees.

French Ministry of Economy and Finance· FranceNVIDIA AI Enterprise · NVIDIA NIM · NVIDIA NeMo Retriever +4