by NVIDIA

NVIDIA BioNeMo Agent Toolkit review, pricing and verdict

Agent-callable skills for protein folding, docking, and genomics on NVIDIA NIM

Best for
Computational biologist
Not for
Non-technical end user with no scientific workflow
  • App connectors
  • Data

Should you use NVIDIA BioNeMo Agent Toolkit?

The BioNeMo Agent Toolkit gives AI agents open-source skills for NVIDIA life-science models, installed with one npx command. NVIDIA reports agent task completion rose from 57.1% to 100% in its own tests. Installing is free, and hosted endpoints need an NVIDIA API key.

Turning a decade of NVIDIA's own accelerated life-science libraries into drop-in, agent-callable skills with a single install command.

NVIDIA controls both the GPU hardware and a decade of proprietary life-science model IP (BioNeMo, Parabricks), making the underlying acceleration hard for a software-only competitor to match.

Also for

  • Bioinformatics engineer
  • Agent/LLM developer adding domain skills
Show 4 more
  • Computational biologists building agent-driven drug discovery pipelines
  • Bioinformatics engineers automating genomic variant calling at scale
  • AI and agent developers adding life-science domain expertise to a general-purpose agent
  • Pharma R&D teams evaluating agentic scientific workflows

Main trade-off

Skills route agent calls correctly but do not improve the accuracy of the underlying scientific models, so outputs still require expert validation.

NVIDIA BioNeMo Agent Toolkit pricing

The toolkit costs nothing to install: scripts are Apache-2.0 and skills and documentation are CC-BY-4.0 per the repository's License section. Most NIM skills call NVIDIA-hosted endpoints with an API key from build.nvidia.com; the repository does not state a rate limit or a price for those endpoints, so check NVIDIA's current terms before relying on them. Local deployment of any model needs a GPU you supply. See NVIDIA and the skills directory for related listings.

Install NVIDIA BioNeMo Agent Toolkit

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit

Before you start

  • Node.js to run the installer
  • An NVIDIA developer API key (nvapi- prefix) for hosted calls
  • A GPU you supply, for local models only

How to invoke it

Installed as SKILL.md packages via 'npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit', then invoked by name by any compatible agent (Claude, Codex, or another runtime); each skill calls an underlying NVIDIA NIM microservice over REST, with MCP server wrappers used for models not yet packaged as NIM.

Works with

  • Claude (Claude Code, Claude Science)
  • Codex
  • Any agent runtime supporting Anthropic Skills or MCP tool-calling

Required runtime

  • Node.js (for the npx skills installer)
  • NVIDIA API key from build.nvidia.com for hosted NIM endpoints
  • Optional local GPU node for self-hosted NIM deployment

Where it runs

  • Web
  • CLI
  • API

Data it can reach

  • protein structures
  • molecular docking and binding scores
  • genomic sequencing reads and variant calls
  • biomarker and single-cell datasets

The permissions this connector asks for, as its own documentation states them.

What NVIDIA BioNeMo Agent Toolkit can do

6 actions an agent can call. Open one for its parameters and an example.

Boltz-2 Structure Prediction and ScoringPredicts protein-ligand complex structures and binding affinity scores for co-folding and validation in protein binder design.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill boltz2-nim --yes

Parameters

ParameterTypeNeededDescription
sequencestringRequiredProtein amino acid sequence (FASTA) to fold.
ligand_smilesstringOptionalSMILES string of a ligand to co-fold and score binding affinity against.

Returns

FieldTypeDescription
structure_pdbstringPredicted 3D structure in PDB/mmCIF format.
confidence_scorenumberPer-residue and complex confidence score.
RFdiffusion Protein Backbone DesignGenerates novel protein backbone scaffolds for binder design workflows using diffusion-based generative modeling.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill rfdiffusion-nim --yes

Parameters

ParameterTypeNeededDescription
target_pdbstringRequiredTarget protein structure to design a binder against.
num_designsnumberdefault 10OptionalNumber of backbone designs to generate.

Returns

FieldTypeDescription
backbone_pdbsarrayGenerated backbone structures as PDB files.
Evo 2 Genomic Sequence AnalysisRuns the Evo 2 foundation model over DNA sequences to predict variant effects and generate genomic sequences.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill evo2-nim --yes

Parameters

ParameterTypeNeededDescription
sequencestringRequiredInput DNA sequence, supported up to megabase-scale context.
taskstringdefault variant_effectOptionalAnalysis task to run: 'variant_effect' or 'generate'.

Returns

FieldTypeDescription
predictionsobjectVariant effect scores or generated sequence output.
OpenFold3 Complex Structure PredictionPredicts protein, nucleic acid, and small-molecule complex structures as an open alternative to closed folding models.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill openfold3-nim --yes

Parameters

ParameterTypeNeededDescription
sequencesarrayRequiredOne or more biomolecule sequences (protein/RNA/DNA) to co-fold.

Returns

FieldTypeDescription
structure_filesarrayPredicted complex structures with per-chain confidence scores.
Parabricks Genomic Variant CallingAccelerates whole-genome and exome variant calling pipelines, cutting hours-long CPU pipelines down to minutes on GPU.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill parabricks --yes

Parameters

ParameterTypeNeededDescription
fastq_inputstringRequiredPath or URL to input FASTQ sequencing reads.
reference_genomestringRequiredReference genome build to align against, e.g. GRCh38.

Returns

FieldTypeDescription
vcf_outputstringVariant call file (VCF) with called variants.
nvMolKit Cheminformatics ScreeningRuns GPU-accelerated molecular similarity search, conformer generation and substructure search; NVIDIA reports up to 3,000x speedups over CPU RDKit pipelines.

Example call

npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill nvmolkit-usage --yes

Parameters

ParameterTypeNeededDescription
smiles_listarrayRequiredList of candidate molecule SMILES strings to screen.
operationstringdefault similarity_searchOptionalOperation to run: 'similarity_search', 'conformer_generation', or 'docking_prep'.

Returns

FieldTypeDescription
ranked_resultsarrayMolecules ranked or filtered by the requested operation.

What NVIDIA BioNeMo Agent Toolkit is for

NVIDIA BioNeMo Agent Toolkit is an open-source GitHub library of agent-callable skills for protein folding, docking, genomics and cheminformatics. It had 495 stars on 2026-10-23, installs with npx skills add, and works in Claude Code, Codex and other SKILL.md runtimes. Installing costs nothing, though compute does.

  • Broad model coverage

    The catalog spans Boltz-2, DiffDock, Evo 2, GenMol, OpenFold3, RFdiffusion, Parabricks and nvMolKit, each as its own installable skill.

  • Three chained workflows

    Protein binder design, generative virtual screening (GenMol, DiffDock, Boltz-2) and MSA-enabled structure prediction ship as ready-made multi-step skills.

  • One-command install

    A single npx command installs the catalog, and flags let you choose one skill or target a specific agent such as Claude Code.

  • Agent-agnostic skill format

    Every skill is a SKILL.md package, so any agent runtime that reads that format can use it, regardless of the backend LLM.

Show all 6 features
  • Open-model setup skills

    Nine RFD4-Proteina skills plus KERMT, CodonFM and Proteina-Complexa set up models on your own hardware instead of calling a hosted NIM.

  • Vendor-reported skill lift

    NVIDIA published its own with-and-without comparison at launch; the repository documents how to rerun a similar test against hosted endpoints.

What people use it for

  • Protein binder design

    An agent chains RFdiffusion to generate candidate backbones and Boltz-2 to fold and score each candidate against a disease target in one automated loop.

  • Genomic variant triage

    An agent runs Parabricks on a patient's FASTQ file to call variants in minutes, then uses Evo 2 to predict which variants likely disrupt protein function.

  • Virtual compound screening

    An agent uses nvMolKit to screen thousands of candidate molecules by similarity before requesting full docking runs, cutting screening time from hours to seconds.

  • Literature-grounded hypothesis generation

    A science agent like Claude Science combines BioNeMo structure predictions with literature search to propose and justify a next experiment.

Strengths and limits

Strengths

  • NVIDIA reports a large task-completion lift on scientific workflows when the skills are attached, a vendor-measured result.
  • Packages Parabricks, nvMolKit and a dozen NIM models as ready-to-call skills instead of custom integration code.
  • Agent-agnostic SKILL.md format works in Claude Code, Codex and other runtimes that read it.
  • Permissive licensing for both code and skill text, with no fee to install or modify.

Limits

  • The skills guide tool use only; model accuracy is unchanged, so uncertain predictions and designed compounds still call for a specialist's check.
  • The repository marks OpenFold3 and the MSA-Search to OpenFold3 workflow as pending validation after hosted runs timed out.
  • Open-model skills run locally, which means a separate checkout of the model weights and a GPU you provide.
  • The repository states no rate limit or price for the hosted NIM endpoints, so production capacity planning means reading NVIDIA's current terms.

NVIDIA BioNeMo Agent Toolkit alternatives

The nearest AI agent skills on Hokai for the same job.

SkillWorks withConnects byChecked
NVIDIA BioNeMo Agent Toolkit This pageClaude · CodexSkill file23 Oct
Easy MCP AITurns a WordPress site into an MCP server that Claude and ChatGPT can run.Claude · ChatGPT · Codex · Cursor +2MCP22 Nov
OMNIGATEx402 gateway for agents: find paid APIs, vet a spend, run budgeted scripts--MCP17 Nov
Personal Agent ProtocolOpen standard for how personal AI agents sign in and act for customers.--Skill file27 Oct

NVIDIA BioNeMo Agent Toolkit facts

Protocol
Custom
Authentication
API key
Latency class
Moderate
Open source
Yes
Maintainer founded
2026
Headquarters
Santa Clara, California, USA
Rate limits
The repository does not state a rate limit for hosted NIM endpoints; check build.nvidia.com for current limits. Self-hosted NIMs run on your own hardware.

What changed

  • Integration Claude Science integration ships source
  • Release NVIDIA launches BioNeMo Agent Toolkit at BIO 2026 (v1.0) source

Questions about NVIDIA BioNeMo Agent Toolkit

What does the NVIDIA BioNeMo Agent Toolkit do?

It is a GitHub library of agent-callable skills that lets an AI agent run NVIDIA life-science software: protein folding with Boltz-2 and OpenFold3, docking with DiffDock, DNA modelling with Evo 2, genomics with Parabricks and cheminformatics with nvMolKit. The repository also bundles three chained workflows and a newer group of open-model setup skills. NVIDIA presented it at its summer life-sciences launch and published its own with-and-without skill comparison.

How do you install the BioNeMo skills?

Run npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit and pick skills interactively, or add --skill boltz2-nim --yes to install one. The --agent flag targets claude-code or codex, and --list browses the catalog without installing. Most NIM skills also need an API key from build.nvidia.com. The open-model skills instead need a separate model checkout and a local GPU.

Which agents can use the toolkit?

The repository documents installs for Claude Code and Codex, and each skill is a SKILL.md package, so any runtime that reads that format can load it. The repository also ships plugin manifests so the toolkit installs through each agent's native plugin flow. NVIDIA says similar results hold across backend LLMs, but that is its statement and the repository publishes no per-model comparison.

Is the BioNeMo Agent Toolkit free?

Installing and reading the skills costs nothing, because the repository carries open licences for both code and skill text. What you pay for is compute. Hosted NIM skills call NVIDIA endpoints with an API key, and the repository states no price or rate limit for them, so read NVIDIA's current terms. Self-hosting a NIM or running the open-model skills needs your own GPU.

What are the limits of the toolkit?

Accuracy comes from the underlying model, not the skill, so a specialist should still check predictions before anyone acts on them. Two OpenFold3-based entries are flagged by NVIDIA as awaiting validation, and deterministic evaluation tasks for local-GPU workflows are still a TODO. The headline lift figure is NVIDIA's own measurement.

About NVIDIA BioNeMo Agent Toolkit

NVIDIA BioNeMo Agent Toolkit is an open-source library of agent-callable skills from NVIDIA that packages its life sciences software, including BioNeMo, Parabricks, nvMolKit and RAPIDS-singlecell, so an AI agent can call it directly. It is not an app a scientist opens. Each skill is a directory with a SKILL.md file, optional reference material and optional scripts, and it tells the agent how to pick the right model, prepare valid inputs, run the job and explain the output across protein folding, docking, generative chemistry, genomics and protein design.

Read the full background

The repository's catalog on 2026-10-23 lists 21 product entries. NIM skills cover Boltz-2, DiffDock, Evo 2, GenMol, MolMIM, MSA-Search, OpenFold2, OpenFold3, ProteinMPNN, RFdiffusion and RFD4-Proteina. Three meta workflows chain them: protein binder design, generative virtual screening (GenMol, then DiffDock, then Boltz-2) and MSA-enabled structure prediction. Library skills wrap Parabricks, nvMolKit and cuEquivariance, and a newer open-models group (RFD4-Proteina setup, Proteina-Complexa, KERMT, CodonFM) sets up models that run on your own hardware. Install is one command, npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit, with --skill to pick one entry and --agent to target Claude Code or OpenAI Codex. The same skills are meant to work in any runtime that reads SKILL.md packages, the format Anthropic introduced for its agents.

NVIDIA announced the toolkit at BIO 2026 on June 23 and reported that agents without the skills completed 57.1% of required scientific tasks on average against 100% with them. That is NVIDIA's own figure, measured on its own task set, and the repository's evaluation section describes the method as running one prompt with and without a skill against the hosted NIM endpoint, graded by trajectory checks and an LLM judge. Native deterministic tasks for workflows that need a local GPU are listed as a TODO.

Who should look elsewhere: the skills raise how reliably an agent calls a model, not how accurate the model is, so low-confidence structures and generated molecules still need expert review. The repository itself says OpenFold3 and the MSA-Search to OpenFold3 workflow are pending validation after hosted runs timed out. The open-model skills need a separate model checkout and your own GPU. A team that wants a general connector library should compare Composio or build its own with the skill-creator skill, and anyone browsing alternatives can start from the skills directory.

Licensing is split. Scripts, tests and build tooling are Apache-2.0, skills and documentation are CC-BY-4.0, and the imported RFD4-Proteina Rosetta helpers are BSD-3-Clause. The GitHub repository showed 495 stars and 77 forks on 2026-10-23.

Sources and guides

More Agent Skills on Hokai

  • AgentCardLet your AI agent pay online with a card it never sees, from the user's Vault or newly issued
  • Link Agent WalletOne-time-use cards from your Link wallet for agents, approved by you
  • find-skillSearch and install skills from the Orthogonal library for agents.
  • DiditIdentity verification, KYB, AML and transaction monitoring an agent can configure and run over a hosted MCP server.
  • ComposioOne MCP endpoint that lets an agent act in 1,500+ apps with managed auth.
  • Pipedrive MCP ServerConnect Claude, ChatGPT and Cursor to your Pipedrive CRM with no code