---
title: "Code & AI agent sandboxes · Where Do I Run This"
description: "Compare code sandboxes by isolation boundary, environment lifetime and assessed capabilities before choosing where an agent runs code."
canonical_url: "https://wheredoirunthis.com/categories/sandboxes"
meta:
  "og:description": "Compare code sandboxes by isolation boundary, environment lifetime and assessed capabilities before choosing where an agent runs code."
  "og:image": "https://wheredoirunthis.com/_og/d/c_WdirtDefault%2Cp_Ii9jYXRlZ29yaWVzL3NhbmRib3hlcyI%2Cs_zzS64TWIpnhGHUrx.png"
  "og:image:height": "630"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "Code & AI agent sandboxes"
  "twitter:image": "https://wheredoirunthis.com/_og/d/c_WdirtDefault%2Cp_Ii9jYXRlZ29yaWVzL3NhbmRib3hlcyI%2Cs_zzS64TWIpnhGHUrx.png"
---

> Index of every page on this site: [llms.txt](https://wheredoirunthis.com/llms.txt)

A guide to choosing where to run

# Code & AI agent sandboxes

Compare code sandboxes by isolation boundary, environment lifetime and assessed capabilities before choosing where an agent runs code.

## **What to check before choosing **

Start with the code you need to contain. Running untrusted commands calls for checking the documented isolation boundary, network controls and access to secrets. A sandbox label alone is not a security guarantee; the atlas records the boundary a product describes rather than ranking its security.

Then check the execution lifecycle: supported languages, setup time, session limits, filesystem persistence and how outputs leave the environment. An interactive agent loop and a short batch job can need very different lifetimes and interfaces.

This list includes every product classified as sandbox, not just products with verified agent-harness integrations. It excludes products classified as persistent environments and pure substrate libraries. Check each profile for evidence of the specific harness and capabilities you need; use the full atlas to explore other product types.

[How we assess products](https://wheredoirunthis.com/method) · [Explore this type in the atlas](https://wheredoirunthis.com/?type=sandbox#atlas)

## **Products in this category **

- [

  **Agent Safehouse**

  macOS-native sandboxing for local agents. Move fast, break nothing.Sandbox · Not disclosedOpen source tool—](https://wheredoirunthis.com/products/agent-safehouse)
- [

  **Agent Sandbox**

  agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).Sandbox · Kata / gVisorOpen source tool—](https://wheredoirunthis.com/products/agent-sandbox)
- [

  **Agent Substrate**

  A secure-by-default agent execution runtime engineered to run millions of sandboxes with 10x higher density than standard container runtimes.Sandbox · Kata / gVisorOpen source tool—](https://wheredoirunthis.com/products/agent-substrate)
- [

  **Agent37**

  Host any agent harness.Sandbox · Kata / gVisorHosted—](https://wheredoirunthis.com/products/agent37)
- [

  **AgentNest**

  The open-source runtime for secure AI agent execution. Disposable, policy-controlled environments for Python, shell, files, packages, browsers, GPUs, and Git work — self-hosted, Python-first, and deliberately not another cloud or cluster orchestrator.Sandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/agentnest)
- [

  **Anthropic Sandbox Runtime (srt)**

  A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.Sandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/sandbox-runtime)
- [

  **AWS Lambda MicroVMs**

  Isolated sandboxes. Near-instant launch and resume. Full lifecycle control.Sandbox · Firecracker microVMHosted—](https://wheredoirunthis.com/products/lambda-microvms)
- [

  **AX (Agent Executor)**

  Declare an agentic task. AX runs it at scale.Sandbox · Kata / gVisorOpen source tool—](https://wheredoirunthis.com/products/ax)
- [

  **Bastion**

  Self-hosted virtual machines for background coding agents.Sandbox · Virtual machineOpen source tool—](https://wheredoirunthis.com/products/bastion)
- [

  **bhatti**

  Your metal. Machines on demand.Sandbox · Virtual machineOpen source tool—](https://wheredoirunthis.com/products/bhatti)
- [

  **Blaxel Sandboxes**

  Give a computer to your agentSandbox · Virtual machineHosted—](https://wheredoirunthis.com/products/blaxel)
- [

  **Boat**

  Persistent Linux VMs for AI agents with SSH, Docker, and fast fork.Sandbox · Virtual machineHosted$20/mo per seat](https://wheredoirunthis.com/products/boat)
- [

  **Brig**

  The microVM sandbox for AI coding agents.Sandbox · Virtual machineOpen source tool—](https://wheredoirunthis.com/products/brig)
- [

  **Browserbase**

  Give your agents access to the whole web.Sandbox · Virtual machineHosted$20/mo](https://wheredoirunthis.com/products/browserbase)
- [

  **Celesto AI**

  Give your agents a Real ComputerSandbox · Virtual machineOpen core—](https://wheredoirunthis.com/products/celesto)
- [

  **Cloudflare Sandboxes**

  Run untrusted code in isolated environments.Sandbox · Firecracker microVMHosted$5/mo](https://wheredoirunthis.com/products/cloudflare-sandboxes)
- [

  **Cube Sandbox (CubeSandbox)**

  Instant, Concurrent, Secure & Lightweight Sandbox Service for AI AgentsSandbox · Kata / gVisorOpen source tool—](https://wheredoirunthis.com/products/cubesandbox)
- [

  **Daytona**

  Secure Infrastructure for Running AI-Generated CodeSandbox · ContainerHosted—](https://wheredoirunthis.com/products/daytona)
- [

  **Docker Sandboxes**

  Run agents safely, local to cloud. — Run Claude Code, Codex, and your other agents at full speed in MicroVM environments. Local or cloud. One CLI.Sandbox · Virtual machineHosted$0.07/h](https://wheredoirunthis.com/products/docker-sandboxes)
- [

  **Drop**

  Linux sandboxing that doesn't get in your waySandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/drop)
- [

  **E2B**

  Every agent gets a machineSandbox · Firecracker microVMOpen core$150/mo](https://wheredoirunthis.com/products/e2b)
- [

  **Fast VM**

  Sandboxing infrastructure for AI — virtual machines that boot in 70ms, zero-downtime snapshots, native branching, 50-90% compute savingsSandbox · Virtual machineHosted—](https://wheredoirunthis.com/products/fastvm)
- [

  **Freestyle**

  Full Linux VMs for AI Agents — Built for complex tasks that run for hours, days, or weeks.Sandbox · Virtual machineHosted$50/mo](https://wheredoirunthis.com/products/freestyle)
- [

  **Gondolin**

  Local Linux micro-VMs with programmable network and filesystem control.Sandbox · Virtual machineOpen source tool—](https://wheredoirunthis.com/products/gondolin)
- [

  **InstaVM**

  Instant computers for AI agentsSandbox · Firecracker microVMHosted$100/mo](https://wheredoirunthis.com/products/instavm)
- [

  **Isorun**

  Sandboxes in milliseconds.Sandbox · Virtual machineHosted$0.04/h](https://wheredoirunthis.com/products/isorun)
- [

  **Judge0**

  Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.Sandbox · ContainerOpen core€27/mo](https://wheredoirunthis.com/products/judge0)
- [

  **Lifo**

  A tiny Linux-like OS in TypeScript, for browsers, Node and serverless functions.Sandbox · Not disclosedOpen source tool—](https://wheredoirunthis.com/products/lifo)
- [

  **microsandbox**

  A computer for anything, anywhere. Open-source microVM sandboxes for AI agents and untrusted code.Sandbox · Virtual machineOpen core$49/mo](https://wheredoirunthis.com/products/microsandbox)
- [

  **nono**

  Ephemeral micro sandboxes for AI agents, with zero setup and zero latency.Sandbox · Not disclosedOpen source tool—](https://wheredoirunthis.com/products/nono)
- [

  **NVIDIA OpenShell**

  The safe, private runtime for fleets of autonomous AI agents.Sandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/openshell)
- [

  **OpenComputer**

  The platform for long-running agents. Define an agent like a serverless function. Choose your model. We handle the runtime.Sandbox · Virtual machineOpen core$20/mo](https://wheredoirunthis.com/products/opencomputer)
- [

  **OpenSandbox**

  Secure, Fast, and Extensible Sandbox runtime for AI agents.Sandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/opensandbox)
- [

  **PandaStack**

  The cloud for AI agents.Sandbox · Firecracker microVMOpen core$20/mo](https://wheredoirunthis.com/products/pandastack)
- [

  **Range**

  Use a remote environment before downloading it.Sandbox · Virtual machineOpen source tool—](https://wheredoirunthis.com/products/range)
- [

  **Runtime**

  Linux sandboxes for AI agentsSandbox · Firecracker microVMHosted—](https://wheredoirunthis.com/products/runtime)
- [

  **Runtime Cloud**

  The AI agent harness for payment teamsSandbox · Not disclosedHosted—](https://wheredoirunthis.com/products/runtm)
- [

  **sandbox-run**

  Run commands in a native Linux namespace sandboxSandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/sandbox-run)
- [

  **sandboxd (formerly sandboxed)**

  Open-source, self-hosted AI app builder.Sandbox · ContainerOpen source tool—](https://wheredoirunthis.com/products/sandboxed)
- [

  **SlicerVM (Slicer)**

  Real Linux, in milliseconds — full Linux microVMs with systemd on your Mac, your servers, or your cloud.Sandbox · Firecracker microVMHosted$25/mo per seat](https://wheredoirunthis.com/products/slicervm)
- [

  **smolvm**

  Branchable microVMs for AI agents.Sandbox · Virtual machineOpen core$20/mo](https://wheredoirunthis.com/products/smolvm)
- [

  **Superconductor**

  The multiplayer AI workspace for teams and coding agentsSandbox · ContainerHosted$128/mo](https://wheredoirunthis.com/products/superconductor)
- [

  **Tencent Cloud Agent Runtime (Agent Sandbox / AGS)**

  A new-generation infrastructure platform built around the agent-native execution paradigm — runtime, sandbox, tools, gateway, memory and observability for agents ('用系统的确定性来收敛 Agent 的不确定性').Sandbox · Kata / gVisorHosted—](https://wheredoirunthis.com/products/tencent-cloud-ags)
- [

  **Vercel Sandbox**

  The safest way to run code you didn’t writeSandbox · Firecracker microVMHosted$20/mo per seat](https://wheredoirunthis.com/products/vercel-sandbox)
- [

  **vmsan**

  Firecracker made simple. Spin up secure microVMs in milliseconds, from install to interactive shell in one command — full lifecycle management, network isolation, Docker image support, and shell access (no SSH).Sandbox · Firecracker microVMOpen source tool—](https://wheredoirunthis.com/products/vmsan)
- [

  **Zeroboot**

  Sub-millisecond VM sandboxes for AI agents via copy-on-write forkingSandbox · Firecracker microVMOpen core—](https://wheredoirunthis.com/products/zeroboot)

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://wheredoirunthis.com/#website","@type":"WebSite","description":"The independent spec sheet for places to run code, and the code your agents write.","name":"Where Do I Run This","url":"https://wheredoirunthis.com/","publisher":{"@id":"https://wheredoirunthis.com/#identity"}},{"@id":"https://wheredoirunthis.com/categories/sandboxes#webpage","description":"Compare code sandboxes by isolation boundary, environment lifetime and assessed capabilities before choosing where an agent runs code.","name":"Code & AI agent sandboxes","url":"/categories/sandboxes","@type":["WebPage","CollectionPage"],"breadcrumb":{"@id":"https://wheredoirunthis.com/categories/sandboxes#breadcrumb"},"isPartOf":{"@id":"https://wheredoirunthis.com/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://wheredoirunthis.com/categories/sandboxes"]}],"primaryImageOfPage":{"@id":"https://wheredoirunthis.com/#logo"}},{"@id":"https://wheredoirunthis.com/#identity","@type":"Organization","name":"Where Do I Run This","url":"https://wheredoirunthis.com","logo":{"@id":"https://wheredoirunthis.com/#logo"}},{"@id":"https://wheredoirunthis.com/categories/sandboxes#breadcrumb","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","name":"The atlas","item":"https://wheredoirunthis.com","position":1},{"@type":"ListItem","name":"Code & AI agent sandboxes","item":"https://wheredoirunthis.com/categories/sandboxes","position":2}]},{"@id":"https://wheredoirunthis.com/#logo","@type":"ImageObject","caption":"Where Do I Run This","contentUrl":"https://wheredoirunthis.com/icon-512.png","inLanguage":"en","url":"https://wheredoirunthis.com/icon-512.png"}]}
```