CubeSandbox

Hardware-isolated microVM sandboxes for AI agents — sub-60ms boot, <5MB overhead, E2B-compatible API, self-hosted on your own KVM nodes.

10,339 999 Rust NOASSERTIONupdated today

agents local

View on GitHub Dispute this mapping →

Curator's take

Reach for CubeSandbox the moment your agents execute model-generated code and "just run it in Docker" stops feeling safe — it gives every tool call a disposable hardware-isolated microVM with E2B's SDK ergonomics, minus the SaaS bill, plus snapshot/rollback of any sandbox state. The catch: it's real infrastructure — you need KVM-capable Linux hosts and someone willing to operate them. Prototyping a single local agent? A container or E2B's hosted tier is less machinery. It's a runtime, not a framework — you still bring LangGraph/AutoGen/whatever on top.

Mapped by ShipWithAI editors · links verified

README.md

CubeSandbox

Instant, Concurrent, Secure & Lightweight Sandbox Service for AI Agents

中文文档 · Quick Start · Documentation · Changelog · X(Twitter)

Cube Sandbox is a high-performance, out-of-the-box secure sandbox service built on RustVMM and KVM. It supports both single-node deployment and easy scaling to multi-node clusters. It is compatible with the E2B SDK and can create a hardware-isolated, fully serviceable sandbox in under 60ms with less than 5MB of memory overhead.

📰 News

	v0.5: AutoPause, Terraform deployer, ARM64 & network policy hardening AutoPause/AutoResume — idle sandboxes auto-suspend and wake on the next request. Terraform one-click cluster deploy ARM64 native full-stack support network policy hardening — per-sandbox traffic tokens, policy-routing egress. Changelog → · Terraform deploy →
	v0.4: Safer egress, easier ops

Continue your stack

What teams reach for next — and why each earns a place beside CubeSandbox. Ranked by curator confidence.

Pairs well with

LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

Why it fitsLangGraph nodes that run model-written code get a disposable, hardware-isolated microVM per execution via the E2B-compatible SDK — crash or escape attempts die with the VM.

AutoGen

Multi-agent conversation framework for building LLM applications with cooperating agents.

Why it fitsAutoGen's code-executor step is the canonical sandbox case: run generated Python in an isolated microVM instead of on the host or a shared container.

paperclip

Open-source control plane for running fleets of heterogeneous AI agents as a "company" — bring your own agent, assign goals, org charts, budgets, governance, and an audited ticket system.

Why it fitspaperclip governs fleets of agents; CubeSandbox is the workload-runtime layer beneath — thousands of <5MB VMs per node, idle agents auto-pause to keep fleet cost sane.

Alternative to See all + compare →

superserve

Persistent, secure sandboxes for AI agents on Firecracker microVMs — TypeScript and Python SDKs, CLI and console; the runtime is a hosted service, the SDK stack is Apache-2.0.

Why it fitsBoth provide Firecracker/microVM sandbox infrastructure for AI agents. CubeSandbox is self-hosted on your own KVM nodes with an E2B-compatible API; Superserve is a hosted service with persistence as the headline and SDKs as the open-source surface.