OpenSandbox
Open-source sandbox platform for running agents on your own infrastructure: isolated environments for code, commands, files, browsers and desktops, from Docker to Kubernetes.
Tags
Description
Start locally with Docker (uvx opensandbox-server) and deploy on Kubernetes behind the same lifecycle API, with resource pools and batch creation for agent evaluation and RL training. The Fast Sandbox runtime uses Firecracker (the README reports 64 ms P50 creation serially) with pause/resume that keeps memory and disk state. Includes per-sandbox egress policies, a unified ingress gateway, a Credential Vault so agents can call external services without seeing real credentials, SDKs for Python, Java/Kotlin, TypeScript, C#/.NET and Go, the osb CLI and an MCP server. Listed in the CNCF Landscape; packages are published under Alibaba namespaces.
Related
- E2B: Open-source, secure cloud sandboxes for AI agents: an isolated machine per agent to run code, browse and use tools.
- Daytona: Secure and elastic infrastructure (sandboxes) for running AI-generated code.
- microsandbox: Easy, fast, programmable, local-first microVM runtime for untrusted workloads.
- Agent Sandbox (Kubernetes SIG Apps): Kubernetes CRD and controller for isolated, stateful, singleton sandbox pods for agent runtimes and RL, with templates, claims and warm pools.
- AIO Sandbox (agent-infra): All-in-one agent sandbox in a single Docker container: browser (VNC/CDP), shell, file system, VS Code Server, Jupyter and MCP sharing one file system.
Guides & comparisons
- Self-hosted sandboxes for agents compared (Comparison): Six ways to isolate agent-run code on hardware you control (OpenSandbox, AIO Sandbox, microsandbox, Kubernetes Agent Sandbox, Anthropic's sandbox-runtime and Docker Sandboxes' local mode) compared on isolation, where they run, agent interface, network and secret controls, maturity and license.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)