Healthcare and Life Sciences - Developer Resources

Agent file: https://developer.nvidia.com/w/meta/healthcare/llms.txt

NVIDIA AI Infrastructure

NVIDIA BioNeMo Agent Toolkit

Changing any agent or AI platform into a life sciences agent.

Built on more than a decade of NVIDIA life sciences libraries, tools, and models, NVIDIA BioNeMo™ Agent Toolkit brings domain-specific tools and skills to the new paradigm of agentic life sciences, where agents, scientists, and labs work together in closed loops to accelerate discovery.

The toolkit provides the full breadth of life sciences computing as agent-callable skills: protein structure prediction, molecular docking, generative chemistry, genomics analysis, protein design, and biomarker discovery. These skills help agents gather evidence, reason over biology and chemistry, run digital experiments, and recommend what scientists should test next.

Visit GitHub

Get Started With Healthcare and Life Sciences Use Cases

Digital Biology

Digital Health

Digital Devices

Generative Protein Binder Design

Intelligently pre-optimize and screen protein binders, dramatically accelerating and improving the drug discovery process.

Genomic Analysis

Easily run essential genomics workflows to save time leveraging NVIDIA® Parabricks®.

Single-Cell Analysis

Accelerate data processing, clustering, dimensionality, reduction, and regression with NVIDIA RAPIDS-singlecell.

NVIDIA-Verified Agent Skills for Digital Biology

NVIDIA-verified agent skills are portable instruction sets that enable AI agents to use NVIDIA Open Models, CUDA-X™ libraries, AI Blueprints, and platform tools effectively. Verified skills are cataloged, scanned for software- and agent-native risks, signed, and documented with a skill card that describes ownership, dependencies, limitations, and verification status. Built on the agentskills.io open skills specification to work reliably across Claude Code, Codex, and Cursor, NVIDIA-verified agent skills help developers understand capabilities, discover where a skill originated, whether it was scanned for common risks, and whether it was modified after publication.

NVIDIA Agent Skills for Digital Biology

BioMedical AI-Q Research Agent

Connect real-world data to reasoning models, enabling secure, privacy-preserving AI workflows that accelerate clinical development by improving research efficiency, insight generation, and decision-making across R&D, trials, and regulatory processes.

Ambient Healthcare Agents

Generative AI reasoning models enable provider and patient voice agents to deliver context-aware responses, automate clinical documentation, personalize patient interactions, and transform workflows for scalable, efficient care.

NVIDIA-Verified Agent Skills for Digital Health

NVIDIA-verified agent skills are portable instruction sets that empower AI agents to leverage NVIDIA Open Models, CUDA-X libraries, AI Blueprints, and platform tools correctly. Verified skills are cataloged, scanned for software- and agent-native risks, signed, and documented with a skill card that describes ownership, dependencies, limitations, and verification status. Built on the agentskills.io open skills specification to work reliably across Claude Code, Codex, and Cursor, NVIDIA-verified agent skills help developers understand capabilities, discover where a skill originated, whether it was scanned for common risks, and whether it was modified after publication.

NVIDIA Agent Skills for Digital Health

Training Healthcare Robotics

Prototype and test advanced robotic systems, train and evaluate AI models with real and synthetic data, develop robotic policies for surgical dexterity, and seamlessly bridge simulation to real-world deployment.

AI-Assisted Annotation

Accelerate and improve the process of labeling medical images

NVIDIA-Verified Agent Skills for MedTech

NVIDIA-verified agent skills are portable instruction sets that empower AI agents to leverage NVIDIA Open Models, CUDA-X libraries, AI Blueprints, and platform tools correctly. Verified skills are cataloged, scanned for software- and agent-native risks, signed, and documented with a skill card that describes ownership, dependencies, limitations, and verification status. Built on the agentskills.io open skills specification to work reliably across Claude Code, Codex, and Cursor, NVIDIA-verified agent skills help developers understand capabilities, discover where a skill originated, whether it was scanned for common risks, and whether it was modified after publication.

NVIDIA Agent Skills for Digital MedTech