NVIDIA OpenShell
Open-source (Apache-2.0) sandboxed runtime that runs autonomous AI agents under policy controls, the software half of NVIDIA's Open Agent Safety Platform.
Find alternatives to NVIDIA OpenShell
What it does
- Guardrails and safety
- Data security
Sources
- Pricing
-
Official documentation · 10 Oct 2026
Apache-2.0 open source; no price stated anywhere (standard s4.1 row 1, open licence).
- Description
-
Official documentation · 10 Oct 2026
Repository description: "OpenShell is the safe, private runtime for autonomous AI agents." Apache-2.0, 0.1.x releases.
- Sold within
-
Official documentation · 10 Oct 2026
Downloaded directly from GitHub under Apache-2.0; no parent offering required.
- Name
-
"consists of NVIDIA OpenShell open source software and the NVIDIA Sentry reference system design."
- URL
-
Official documentation · 10 Oct 2026
NVIDIA's OpenShell documentation; source at https://github.com/NVIDIA/OpenShell.
- Deployment
-
Official documentation · 10 Oct 2026
Installed by a shell script (CLI and gateway) on the user's own machines.
- Interfaces
-
Official documentation · 10 Oct 2026
CLI plus SDKs for Python (uv add openshell), npm, Go and Cargo.
Also from NVIDIA
-
NVIDIA AI Enterprise Platform
Supported software suite for building and deploying AI workloads on NVIDIA hardware.
-
NVIDIA Blackwell Hardware
Data-centre GPU architecture used for training and serving large models, sold in servers and rack systems.
-
CUDA Toolkit Platform
Programming toolkit and libraries for running general-purpose computation on NVIDIA GPUs.
-
NVIDIA DGX Cloud Infrastructure service
NVIDIA's AI cloud of GPU clusters and managed AI services, which NVIDIA's own page now presents as its internal environment for building its models, and which is still sold on Microsoft's Azure marketplace.
-
NVIDIA DRIVE Platform
End-to-end autonomous-vehicle platform spanning training infrastructure, simulation and safety-certified in-vehicle compute for production autonomy from L2++ to L4.
-
NVIDIA Isaac Platform
Open robotics development platform combining simulation, CUDA-accelerated perception libraries, ROS 2 integration and humanoid tooling for building AI-powered robots.
-
NVIDIA NeMo Platform
Suite of libraries and microservices covering the AI agent lifecycle - data curation, customisation, evaluation, guardrails and monitoring.
-
NVIDIA NIM Model API
Prebuilt inference microservices that package foundation models with optimised serving engines and standard APIs, deployable as hosted endpoints or self-hosted containers.
-
NVIDIA Omniverse Platform
Platform of OpenUSD-based libraries and microservices for building simulation-ready digital twins and synthetic-data environments used to train and validate physical AI and robots.
-
NVIDIA Vera Rubin Hardware
NVIDIA's data-centre platform succeeding Blackwell, pairing Rubin GPUs with Vera CPUs at rack scale for agentic AI and reasoning workloads.
-
NVIDIA ACE Platform
Suite of AI technologies (speech, intelligence, animation models and plugins) for building conversational, actionable in-game characters, mostly MIT-licensed with some components under NVIDIA's open model license.
-
NVIDIA AI Workbench Platform
Free development-environment manager for creating, customizing and collaborating on AI applications across GPU systems, with enterprise support available through an NVIDIA AI Enterprise license.
-
NVIDIA BioNeMo Platform
Development platform for AI-driven biology and drug discovery: open models, libraries, datasets and NIM microservices for the full AI lifecycle in biopharma.
-
NVIDIA BlueField Platform Hardware
Data-processing-unit (DPU) platform combining compute with accelerated networking, storage and security for AI-factory infrastructure.
-
NVIDIA Broadcast Hardware
Free application that enhances livestreams and video calls with AI noise removal, background replacement and other audio/video effects; requires a GeForce RTX GPU.
-
NVIDIA DGX Spark Hardware
Desktop AI supercomputer powered by the GB10 Grace Blackwell Superchip for local autonomous agents, running models up to 200B parameters for inference.
-
NVIDIA DGX Station Hardware
Deskside AI supercomputer powered by the GB300 Grace Blackwell Ultra Superchip, up to 20 petaFLOPS and 748GB coherent memory, supporting models up to 1T parameters.
-
Open-source model-deployment server for TensorRT, PyTorch, ONNX, OpenVINO and other frameworks across GPUs and CPUs, with production support and stable APIs through NVIDIA AI Enterprise.
-
NVIDIA HGX Platform Hardware
Reference baseboard specification (HGX B200, B300, Vera Rubin NVL8) that system integrators and OEMs build into complete AI servers, listed in NVIDIA's Qualified System Catalog.
-
NVIDIA IGX Platform Hardware
Edge-AI developer kits (IGX Thor, IGX Thor Mini, IGX Orin) for industrial and medical edge computing.
-
NVIDIA Jetson Hardware
Family of embedded AI modules and developer kits for robotics and edge AI (Thor, AGX Orin, Orin NX/Nano, Xavier, TX2/Nano series).
-
NVIDIA OVX Systems Hardware
Scalable data-centre server systems (e.g. OVX L40S with four or eight GPUs) for AI and graphics workloads, built by NVIDIA OVX partners.
-
NVIDIA Quantum-X InfiniBand Hardware
Quantum-X800 InfiniBand switching for large-scale AI clusters, part of NVIDIA's InfiniBand networking line.
-
NVIDIA RAPIDS Platform
Suite of open-source, GPU-accelerated data-science libraries (cuDF, cuML, cuGraph, cuxfilter), rebranding to "CUDA-X for Data Science."
-
NVIDIA Riva Platform
Deployable speech-AI library (ASR/TTS) for production inference, free to prototype via build.nvidia.com and licensed for production deployment through NVIDIA AI Enterprise.
-
NVIDIA RTX PRO Hardware
Professional GPU line (RTX PRO 2000 through RTX PRO 6000) for AI, graphics and simulation workloads across Blackwell, Ada Lovelace, Ampere and Turing architectures.
-
NVIDIA Spectrum-X Hardware
Ethernet networking platform (switches, ConnectX SuperNICs, BlueField DPUs, LinkX cables) purpose-built for generative-AI-scale data centres.
-
NVIDIA TensorRT Platform
Ecosystem of compilers, runtimes and optimization tools for high-performance deep-learning inference; TensorRT-LLM and Model Optimizer are free on GitHub, with commercial deployment options via NVIDIA AI Enterprise.
-
NVIDIA Virtual GPU (vGPU) Hardware
Software that virtualizes GPUs across VMs in enterprise data centres and cloud deployments, licensed through NVIDIA's vGPU License and Support Portal.
-
NVIDIA AI Foundry Platform
NVIDIA AI Foundry provides a platform and service for building generative AI models using enterprise data.
-
NVIDIA AI for Media Platform
NVIDIA AI for Media supplies AI tools and microservices for enhancing audio, video and visual effects.
-
NVIDIA Canvas Application
NVIDIA Canvas uses AI to turn brushstrokes into landscape images.
-
NVIDIA Cosmos Dataset Search Application
Cosmos Dataset Search ingests, indexes, searches and curates multimodal data using visual search and analytics microservices.
-
NVIDIA DLSS Application
NVIDIA DLSS uses AI neural rendering to generate frames and improve image quality in supported games and applications.
-
NVIDIA Mission Control Infrastructure service
NVIDIA Mission Control manages AI infrastructure through workload orchestration, monitoring and automated recovery.
-
NVIDIA NeMo Studio Application
NeMo Studio supplies a web interface for managing Helix resources and inspecting AI agents, jobs and telemetry.
-
NVIDIA Run:ai Infrastructure service
NVIDIA Run:ai orchestrates AI workloads and allocates GPU resources across Kubernetes infrastructure.
-
Project G-Assist AI agent
Project G-Assist uses voice or text commands to adjust PC settings and provide system diagnostics.
-
NVIDIA Megatron Core Developer tool
NVIDIA Megatron Core provides GPU building blocks for training generative AI models.
-
Transformer Engine Developer tool
Transformer Engine accelerates Transformer model training and inference on NVIDIA GPUs using low-precision formats.
-
NVIDIA Data Loading Library (DALI) Developer tool
NVIDIA Data Loading Library (DALI) loads and preprocesses image, video and audio data for deep learning.
-
NVIDIA cuML Developer tool
NVIDIA cuML accelerates scikit-learn, UMAP and HDBSCAN machine learning workflows on GPUs.
-
NVIDIA cuVS Developer tool
NVIDIA cuVS provides GPU-accelerated vector search and data clustering.
-
NVIDIA cuEquivariance Developer tool
NVIDIA cuEquivariance provides CUDA kernels and APIs for geometric neural networks.
-
NIXL Developer tool
NIXL accelerates transfers among GPU memory, CPU memory and storage for AI inference frameworks.
-
NVIDIA DGX H100 Hardware
NVIDIA DGX H100 is an AI computing system containing eight NVIDIA H100 GPUs.
-
NVIDIA DGX B300 Hardware
An AI computing system powered by NVIDIA Blackwell Ultra GPUs for model inference and training.
-
NVIDIA Holoscan Platform
A computing platform for real-time processing of streaming sensor data and AI inference.
-
NVIDIA TensorRT LLM Infrastructure service
A library and runtime for optimizing large-language-model inference on NVIDIA GPUs.
-
NVIDIA Metropolis Platform
NVIDIA Metropolis is a platform for developing and deploying video analytics AI agents and applications.
-
NVIDIA Open Agent Safety Platform Platform
A software platform and reference system design that monitors and governs AI agent behavior.
-
NVIDIA AI Aerial Platform
A suite of computing platforms, software libraries and tools for building, training, simulating and deploying AI-native wireless networks.
-
NVIDIA NemoClaw Agent platform
An agent deployment package that combines models, harnesses, tools and a runtime with policy controls and sandboxing.
-
NVIDIA Earth-2 Platform
A software platform for weather and climate forecasting that includes models, tools and services.
Something wrong here? Send a correction — quote this product id: nvidia-openshell.