NVIDIA BioNeMo Agent Toolkit provides AI agents and scientific software systems with tools for computational life sciences workflows, including protein structure prediction, molecular docking, generative chemistry, genomic analysis, protein design, and biomarker discovery.
The toolkit combines NVIDIA life sciences libraries, tools, and open models. It is intended for agents and lab systems that gather evidence, compare findings, run experiments, and recommend next steps. Target users include general-purpose assistants, specialized scientific agents, software platforms, and in-house biopharma systems that need to synthesize scientific knowledge, call models, evaluate results, and execute follow-on tasks.
NVIDIA said more than 50 companies are using the toolkit. The system includes NVIDIA BioNeMo and uses NVIDIA NIM microservices, NVIDIA Parabricks, NVIDIA NeMo, NVIDIA Nemotron technologies, accelerated computing, and agent-callable skills.
“Frontier models are the brains. BioNeMo is the scientific toolbox. Together, they give AI agents the skills of a PhD research assistant and the speed of a supercomputer,” said Jensen Huang, founder and CEO of NVIDIA. “For the first time, researchers can build AI agents that understand scientific knowledge, use scientific tools and execute scientific workflows. This is a new way to do science – one that can dramatically accelerate discovery across biology, chemistry, genomics and medicine.”
Open model and research organizations, including the Arc Institute, Open Molecular Software Foundation and the University of Washington’s Institute for Protein Design (IPD) are working with NVIDIA on BioNeMo-based agent workflows. The Institute for Protein Design collaboration has improved runtimes for bio-design models such as RosettaFold3, delivering 2x faster performance than the prior-generation model.
“Every tool we’ve built for protein design is only as powerful as the scientists who can efficiently access it,” said David Baker, professor of biochemistry at the University of Washington School of Medicine and director of the Institute for Protein Design. “The next leap in science won’t come from a single discovery; it will come from the speed of iterative designs and agents that can repeatedly reason through the complexity of biology at a speed humans never could.”
Agent-Ready Tools for Life Sciences
NVIDIA is developing BioNeMo Agent Toolkit for life sciences R&D workflows. Global scientific R&D spending has reached $3.8 trillion, while annual pharmaceutical budgets are approaching $300 billion. The toolkit is designed to help developers build life sciences agents that can run experiments, process results, and connect hypothesis generation with discovery workflows. Some companies are extending those workflows into physical labs.
BioNeMo Agent Toolkit lets agents call defined tools, interpret outputs, and return scientific results through structured workflows. NVIDIA is converting BioNeMo libraries, models, and frameworks into tools that agents can call.
The NVIDIA Agent Toolkit technologies including NVIDIA Nemotron open models for reasoning, the NVIDIA NeMo RL library for reinforcement learning and NVIDIA NemoClaw blueprints for private agents that can reason across tasks, call tools and interact with data continuously.
NVIDIA NIM microservices allow agents to call models and run specific tasks. The NVIDIA OpenShell runtime provides a controlled execution environment.
The toolkit’s components support workflows including:
- Virtual Screening: Agents can generate and screen compounds, dock them to a target, predict binding strength, filter for drug-like properties, and output candidates for prioritization. The workflow can reduce screening time from days to minutes.
- Genomic Analysis and Target Discovery: Agents can process raw sequencing data into genetic insights and biological targets. NVIDIA Parabricks accelerates alignment and variant calling, while genomic foundation models score variant effects and agents rank disease-relevant candidates for further study.
- Protein Binder Design: Agents can help researchers design and validate candidates computationally before lab work begins.
- Deep Biomedical Research: NVIDIA Biomedical AI-Q Research Agent connects real-world data to reasoning models for literature review, protocol generation, clinical trial screening, and pharmacovigilance.
- Medical Imaging Analysis: Agents can process, segment, synthesize, and analyze medical imaging data to support biomarker discovery.
Life Sciences Organizations Use NVIDIA BioNeMo
Technology and life sciences companies are using BioNeMo Agent Toolkit for agentic workflows. AI research and scientific agent builders, including Anthropic, Edison Scientific, Lila Sciences, OpenAI, and Owkin, are integrating BioNeMo to support agents that move beyond question answering into scientific task execution.
Scientific data and workflow platforms from Benchling, Certara, Databricks, Snowflake, and Seqera are using BioNeMo Agent Toolkit to connect data systems with AI-based scientific workflows. BioNeMo skills can help agents query biological and chemical datasets, prepare model-ready inputs, launch reproducible workflows, analyze outputs, and return results within software used by scientists.
Diagnostics and pharmaceutical companies, including Lilly and Natera, are using BioNeMo Agent Toolkit to build repeatable workflows across discovery, translational research, and clinical insight. AI-native biology companies, including Boltz, Basecamp Research, Chai Discovery, Dyno, PerturbAI, and Proxima, have worked with NVIDIA on tools for model-based therapeutic design workflows.
Computer-aided drug discovery software providers, including Dassault Systèmes, Cadence through OpenEye, and Schrödinger, are integrating the toolkit’s capabilities into scientific applications used by discovery teams. Agents can coordinate molecular generation, docking, and prediction so researchers can ask questions, launch analyses, and identify next steps inside computer-aided design software.
Lab instrument and automation companies, including Automata, HighRes, Tecan, Thermo Fisher, and the autonomous data generation platform Medra, are connecting lab systems with computational discovery workflows using BioNeMo skills.
AI cloud and infrastructure companies, including Baseten, Modal, and Nebius, are using the toolkit to help developers build hosted life sciences workflows. The companies are supporting BioNeMo through application programming interfaces, managed compute, and production inference environments.
Availability
BioNeMo Agent Toolkit and skills are available now through the NVIDIA developer resources page and GitHub.
Source: NVIDIA
About NVIDIA
NVIDIA, founded in 1993 and headquartered in Santa Clara, CA, designs and manufactures graphics processing units, systems on chips, networking hardware, and AI intelligence software such as CUDA. Its products serve industries including gaming, data centers, autonomous vehicles, professional visualization, robotics, health care, and energy. The company introduced the GPU in 1999 and later expanded into accelerated computing and AI infrastructure. In gaming, its GPUs support high-performance rendering, while in AI and high-performance computing, its systems provide the infrastructure for training and deploying large-scale models. NVIDIA also develops tools for robotics and autonomous driving.