AI PlatformAI-native

NVIDIA Isaac GR00T

Name: NVIDIA Isaac GR00T
Brand: NVIDIA

Open reference platform from NVIDIA for general-purpose humanoid robots: GR00T foundation model (N1, N1.5), data (Cosmos), simulation (Isaac Sim / Lab, Newton) and Jetson AGX Thor runtime.

Producer:NVIDIAOn-Premises · Edge · HybridReleased:Mar 18, 2024

Regional availability·0 regions

global-developer-program

Data residencySovereign cloud

Visit platform

Supported models

6SLM/LLM

SDK / Languages

2python, c_cpp

Robotics-Ready

✓

Description

NVIDIA Isaac GR00T (Generalist Robot 00 Technology) is an open reference platform for general-purpose humanoid robots. It comprises open data and data pipelines, an open robot foundation model (GR00T N1), simulation frameworks built on NVIDIA Omniverse and Cosmos, middleware, CUDA-X accelerated runtime libraries, and NVIDIA Jetson Thor for real-time robot inference and control.

GR00T models are multimodal (language + images) and cross-embodiment — runnable across diverse humanoid form factors. They are trained on real teleoperation data, synthetic data (GR00T-Dreams, GR00T-Mimic) and internet-scale video, and are adaptable via post-training for specific embodiments, tasks and environments. The workflow spans synthetic data generation, training, evaluation in simulation, and deployment on target hardware.

MLOps Lifecycle

11/17 supported

Model Registry

Versioning — model artifact versioning

Approval workflows — approval workflow before production

Immutable artifacts — immutability of stored versions

Lineage tracking — tracking data and model relationships

2 / 4 supported · 2 unsupported hidden

Feature Store

Online serving — real-time feature serving

Offline storage — feature storage for training

Streaming ingestion — streaming ingestion (Kafka, Flink)

2 / 3 supported · 1 unsupported hidden

Prompt Management

Prompt registry — central prompt repository

Versioning — prompt versioning and history

Testing frameworks — A/B testing and prompt evaluation

1 / 3 supported · 2 unsupported hidden

Monitoring

Data drift detection — input data drift detection

Concept drift detection — concept drift detection

Hallucination monitoring — LLM hallucination monitoring

Bias evaluation tools — bias evaluation tooling

3 / 4 supported · 1 unsupported hidden

Human-in-the-Loop

Labeling services — data labeling tools

RLHF workflows — reinforcement learning from human feedback

Manual override — manual override of model decisions

3 / 3 supported · none unsupported

Data & Knowledge

Applications

Security

Developer Ecosystem

SDK Languages

PyPythonC+C / C++

API Type

RESTgRPC

Community & resources

Templates library

Quickstarts

API Reference

Tutorials

Pricing & Business Model

See full pricing

Pricing models

Tiered subscription

Resource quotas

Per project

Per user

Cost alerting

SLA & Support

CommunityEnterprise 24/7

Supported AI Models

Robotics & Humanoids Extension

Robotics-Ready

Robotics standards

URDF Support
OpenUSD Interoperability
Sim-to-Real Pipelines

Edge Orchestration

OTA updates (over-the-air)
Real-time kernel support

Sources

Sustainability

Carbon footprint tracking

aiPlatforms.sustainability.renewableEnergy

GR00T workloads target NVIDIA Blackwell accelerators and Jetson AGX Thor edge modules — energy efficiency figures are reported at the deployment level, not the platform itself.

Description

MLOps LifecycleiMLOps LifecycleFull model lifecycle: registry, feature store, prompt management, monitoring and human-in-the-loop.

Model Registry

Feature Store

Prompt Management

Monitoring

Human-in-the-Loop

Data & KnowledgeiData & Knowledge ManagementData connectors, vector database integration, native vector search and data management (PII, provenance, synthetic data).

ApplicationsiAI ApplicationsDomains and use cases this platform is best suited for — from RAG and fine-tuning to scientific research.

Architecture & MechanismsiArchitecture & MechanismsArchitectural foundations and modern AI processing methods that are natively supported or used by this platform.

SecurityiEnterprise SecurityCertifications, access controls and data-protection features essential for corporate deployments and cloud privacy compliance.

Developer EcosystemiDeveloper EcosystemDeveloper resources: available SDKs, supported programming languages, and infrastructure features and model-deployment methods.

Pricing & Business ModeliPricing & Business ModelBilling models (usage-based, provisioned throughput), resource limits and SLA parameters (uptime, support tiers).