NVIDIA OpenShellNVIDIA
|
Teleport BeamsTeleport
|
|||||
| NVIDIA OpenShell | Teleport Beams | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
NVIDIA OpenShell:
About
NVIDIA OpenShell is an open, secure runtime for autonomous AI agents that governs how agents execute, what they can access, and where inference traffic goes. Security is enforced in the environment rather than inside the model or application: nothing is permitted by default, permissions are granted through policy, and enforcement happens outside the agent process so it cannot be bypassed through prompting. Each agent runs in an isolated sandbox with no direct network access, limited file access, and kernel-level monitoring of system calls. A gateway acts as the control plane, authenticating users, managing sandbox lifecycles, and delivering policies, settings, credentials, and inference configuration. A supervisor runs outside each sandbox, evaluates network requests against policy at the binary, destination, method, and path levels, and provides credentials only when allowed.
|
Teleport Beams:
About
Teleport Beams is a cloud-hosted runtime for building, testing, and running AI agents that need controlled access to infrastructure and inference services. It provisions short-lived, isolated microVMs with delegated identities, virtual networking, and audit records, avoiding the need to place long-lived API keys or credentials inside agent environments. Teams can create reusable Phase images to preserve project files and setup across runtime sessions, run agents against internal applications and databases, and develop or test applications in isolated environments. Beams provides a command-line workflow for creating, managing, and publishing workloads, plus controls for access, session review, and agent activity. It is intended for engineering, platform, and security teams deploying agentic workflows against cloud or other Teleport-protected resources.
|
|||||
NVIDIA OpenShell:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Teleport Beams:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
NVIDIA OpenShell:
Audience
Developers, platform teams, and security or IT teams seeking to run autonomous AI agents with sandboxing, policy enforcement, credential controls, inference routing, and auditable access boundaries
|
Teleport Beams:
Audience
Engineering, platform, and security teams building and operating AI agents that need controlled access to infrastructure, internal applications, databases, or inference services.
|
|||||
NVIDIA OpenShell:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Teleport Beams:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
NVIDIA OpenShell:
API
Offers API
Not Supported
|
Teleport Beams:
API
Offers API
Supported
|
|||||
NVIDIA OpenShell:
Screenshots and Videos |
Teleport Beams:
Screenshots and VideosNo images available
|
|||||
NVIDIA OpenShell:
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Teleport Beams:
Pricing
$150/month
The Pro plan is $150 per month and includes 150 beam-hours, 5 monthly active users, 25 protected resources, and 300 GB of egress. Additional compute is $0.50 per beam-hour and egress above the included allowance is $0.10 per GB. Enterprise pricing is custom.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
NVIDIA OpenShell:
Reviews/
|
Teleport Beams:
Reviews/
|
|||||
NVIDIA OpenShell:
Training
Documentation
Supported
Webinars
Supported
Live Online
Not Supported
In Person
Not Supported
|
Teleport Beams:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
NVIDIA OpenShell:
Company InformationNVIDIA
Founded: 1993
United States
www.nvidia.com/en-us/ai/openshell/
|
Teleport Beams:
Company InformationTeleport
Founded: 2015
United States
www.beams.run/
|
|||||
NVIDIA OpenShell:
Alternatives |
Teleport Beams:
AlternativesNo Alternatives
|
|||||
|
NVIDIA OpenShell:
|
||||||
| NVIDIA OpenShell: | ||||||
|
NVIDIA OpenShell:
|
||||||
| NVIDIA OpenShell: | Teleport Beams: | |||||
NVIDIA OpenShell:
Categories |
Teleport Beams:
Categories |
|||||
NVIDIA OpenShell:
Integrations
Amazon Bedrock
Not Supported
Claude Code
Not Supported
Globster
Supported
Goose
Not Supported
Hawcx
Supported
Model Context Protocol (MCP)
Not Supported
NVIDIA Open Agent Safety Platform
Supported
Odile Gate
Supported
OpenAI Codex
Not Supported
OpenCode
Not Supported
|
Teleport Beams:
Integrations
Amazon Bedrock
Supported
Claude Code
Supported
Globster
Not Supported
Goose
Supported
Hawcx
Not Supported
Model Context Protocol (MCP)
Supported
NVIDIA Open Agent Safety Platform
Not Supported
Odile Gate
Not Supported
OpenAI Codex
Supported
OpenCode
Supported
|
|||||
|
NVIDIA OpenShell:
|
Teleport Beams:
|