kubernetes-sigs/agent-sandbox

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

About the project

Agent Sandbox is a Kubernetes extension for managing isolated, stateful workloads that run as single long-lived containers with stable identities and persistent storage. It is intended for AI agent runtimes, reinforcement-learning workloads, and other applications that do not fit ordinary stateless deployments. Its catalogue skills and instructions support operating these sandbox workloads.

Latest release v1.0.1 · 3 Sept 2026

These files are kubernetes-sigs/agent-sandbox's own configuration. They tell Claude Code, Codex, GitHub Copilot and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

3,750Stars on the repository
9Files it configures its agents with
4,625Tokens loaded in every session
4Agents configured

Instructions

Skills