Esta página se muestra en inglés. Una traducción al español está en curso.
SkillsMay 11, 2026·2 min de lectura

Agent Sandbox — Run Agents Safely on Kubernetes

Agent Sandbox provides Kubernetes-first guardrails for agent workloads: resource limits, isolation, and repeatable environments so failures stay contained.

AI Open Source
AI Open Source · Community
Listo para agents

Instalación lista para agent

Este activo puede instalarse después de elegir el runtime, revisar el plan y ejecutar el comando correspondiente.

Native · 98/100Política: permitir
Superficie agent
Cualquier agent MCP/CLI
Tipo
Skill
Instalación
Single
Confianza
Confianza: Established
Entrada
Asset
Comando de instalación directa
npx -y tokrepo@latest install 3f94c7c7-7f5e-4e7e-8a42-d3c4fd46eaff --target codex

Ejecutar después de confirmar el plan con dry-run.

Introducción

Agent Sandbox provides Kubernetes-first guardrails for agent workloads: resource limits, isolation, and repeatable environments so failures stay contained.

  • Best for: Teams running untrusted agent code who need isolation, quotas, and an auditable execution surface
  • Works with: Kubernetes clusters + CI; pair with policy-as-code and least-privilege service accounts
  • Setup time: 30 minutes

Practical Notes

  • Setup time ~30 minutes (apply manifests + run one sandboxed job)
  • Three hard checks: limits enforced, egress scoped, run logs retained
  • GitHub stars + forks (verified): see Source & Thanks

Agents get dangerous when they can run arbitrary code with long-lived credentials. A Kubernetes sandbox lets you bound blast radius: small quotas, short-lived identities, and auditable logs. Use it to make ‘agent execution’ an infrastructure primitive rather than an ad-hoc local script.

FAQ

Q: Do I need Kubernetes for agents? A: Not always—but it’s a strong default if you must isolate untrusted execution.

Q: What’s the first guardrail to add? A: Resource limits + restricted service accounts; then add egress controls.

Q: How do I make runs reproducible? A: Pin images/versions and treat manifests as code reviewed like any PR.

🙏

Fuente y agradecimientos

Source: https://github.com/kubernetes-sigs/agent-sandbox > License: Apache-2.0 > GitHub stars: 2,125 · forks: 253

Discusión

Inicia sesión para unirte a la discusión.
Aún no hay comentarios. Sé el primero en compartir tus ideas.

Activos relacionados

CubeSandbox — Lightweight AI Agent Sandbox by Tencent

An instant, concurrent, and secure sandbox runtime for AI agents developed by Tencent Cloud. CubeSandbox provides lightweight container-based isolation for agent code execution with fast startup times.

Configs
AI Open Source

Agent Safehouse — Sandbox macOS Coding Agents

Agent Safehouse sandboxes local coding agents on macOS using sandbox-exec deny-first profiles, limiting access to only approved files and integrations.

Skills
Agent Toolkit

OpenAI Agents JS — TypeScript Multi-Agent SDK

OpenAI Agents JS brings multi-agent workflows to TypeScript with provider-agnostic runs, zod schemas, tracing hooks, and sandbox agent patterns.

Skills
OpenAI

OpenSandbox — Secure AI Agent Sandbox by Alibaba

An open-source sandbox runtime by Alibaba for running AI agent code safely, providing fast startup, strong isolation, and extensible tool integration.

Scripts
Script Depot
◈Inicio🔍Buscar👤Yo