| layout |
home |
| hero |
| name |
text |
tagline |
actions |
OpenSandbox |
Universal Sandbox Infrastructure for AI Applications |
Securely run commands, filesystems, code interpreters, browsers, and developer tools in isolated runtime environments. |
| theme |
text |
link |
brand |
Quick Start |
/overview/home |
|
| theme |
text |
link |
alt |
Explore Architecture |
/overview/architecture |
|
|
|
| features |
| title |
details |
Sandbox Lifecycle and Runtime Management |
Provision, monitor, renew, and terminate sandbox instances with Docker and Kubernetes-oriented runtime capabilities. |
|
| title |
details |
Multi-Language SDKs and Unified APIs |
Build with Python, Java/Kotlin, and JavaScript SDKs on top of standardized lifecycle and execution protocols. |
|
| title |
details |
Powerful In-Sandbox Execution |
Execute shell commands, manage files, run multi-language code interpreters, expose ports, and stream logs/metrics. |
|
| title |
details |
Built for Real AI Workloads |
Supports coding agents, browser automation, remote development, AI code execution, and RL training scenarios. |
|
|
OpenSandbox is now listed in the CNCF Landscape.
Run Claude Code, Gemini CLI, Codex, and other agent tools in isolated sandboxes.
Execute Chrome and Playwright workloads with controlled runtime, filesystem, and networking.
Host VS Code Web and desktop-like environments for secure cloud development workflows.
Run model-generated code safely, stream outputs, and iterate quickly with reproducible environments.
Launch reinforcement learning tasks with managed sandbox lifecycle and resource controls.
Explore all scenario references in Examples.