+
+

Related Products

  • BAND
    3 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    999 Ratings
    Visit Website
  • DataHub
    10 Ratings
    Visit Website
  • MOVEit
    625 Ratings
    Visit Website
  • Bluepear
    55 Ratings
    Visit Website
  • cside
    37 Ratings
    Visit Website
  • Reflectiz
    33 Ratings
    Visit Website
  • ThreatLocker
    700 Ratings
    Visit Website
  • Checksum.ai
    1 Rating
    Visit Website
  • Ethena
    131 Ratings
    Visit Website

About

Kastra is the authorization layer for AI systems, deciding what agents, models, and AI tools are allowed to do before they do it. It sits in the execution path of every prompt, tool call, shell command, database operation, and API request, evaluates each action against deterministic, attribute-based policy, and returns an allow, deny, redact, or escalate decision in under a millisecond. Unlike monitoring products that observe AI after it acts, Kastra blocks unauthorized behavior before it reaches a tool, API, database, or production system. Its unified control plane combines a policy engine, edge decision points, integrations, and a tamper-evident evidence vault that signs every decision for audit and replay. Kastra Edge brings local enforcement to developer machines, protecting Claude Code, Cursor, Codex CLI, and other coding agents from destructive commands, secret exfiltration, unsafe file writes, and unauthorized tool use.

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.

Platforms Supported

Windows Not Supported
Mac Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

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

Audience

AI engineering and security teams that need to enforce authorization policies and audit every action performed by AI systems before execution

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

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

$19.99 per month
Free Version Supported
Free Trial Not Supported

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported

Training

Documentation Supported
Webinars Supported
Live Online Not Supported
In Person Not Supported

Company Information

Kastra
Founded: 2026
United States
kastra.ai/

Company Information

NVIDIA
Founded: 1993
United States
www.nvidia.com/en-us/ai/openshell/

Alternatives

Alternatives

nono

nono

Always Further
IronClaw

IronClaw

Near AI

Categories

AI Governance Supported

Categories

Agentic AI Supported

Integrations

Claude Code Supported
Codex CLI Supported
Cursor Supported
Go Supported
Google Sheets Supported
JSON Supported
Java Supported
Microsoft Excel Supported
NVIDIA Open Agent Safety Platform Not Supported
OpenAI Supported
OpenClaw Supported
Python Supported
Rust Supported
Slack Supported
Swift Supported
TypeScript Supported
YAML Supported

Integrations

Claude Code Not Supported
Codex CLI Not Supported
Cursor Not Supported
Go Not Supported
Google Sheets Not Supported
JSON Not Supported
Java Not Supported
Microsoft Excel Not Supported
NVIDIA Open Agent Safety Platform Supported
OpenAI Not Supported
OpenClaw Not Supported
Python Not Supported
Rust Not Supported
Slack Not Supported
Swift Not Supported
TypeScript Not Supported
YAML Not Supported
Claim Kastra and update features and information
Claim Kastra and update features and information
Claim NVIDIA OpenShell and update features and information
Claim NVIDIA OpenShell and update features and information