AI agent sandbox providers compared

Agent37 hosts persistent sandboxes for agent harnesses such as Claude Code, Codex and OpenClaw, priced per minute.

Cloud computers for AI agents running in Firecracker instances, with snapshots and published ports.

Alibaba Cloud's E2B-compatible VM-isolated agent sandbox (Flash and Container editions) billed per second per vCPU/GiB.

Alibaba Cloud's on-demand cloud sandboxes for AI agents: Linux and Windows computers, browsers, code sandboxes and Android phones.

Open-source tool for running isolated coding-agent VMs on your own machines, your cloud accounts, or Amika-hosted devboxes.

Remote Debian machines where the Amp coding agent works on a thread, pausing when idle and waking with files and processes intact.

Serverless runtime and persistent Firecracker sandboxes for agents, built on Archil's shared disks and object-storage filesystems.

Managed AWS services for agents: Runtime hosts agents in per-session microVMs, Code Interpreter runs code in a sandbox.

AWS Firecracker-based MicroVMs for sandboxes, suspend/resume with memory and disk preserved, built from a Dockerfile image.

Azure service of prewarmed, Hyper-V-isolated sessions for running untrusted or AI-generated code, via code interpreter or custom containers.

Sandboxed code-execution API for AI agents (Bash, Python, Node) with stateful threads, credit pricing and Kubernetes self-hosting.

Python-first sandboxes on Beam's serverless platform, with snapshots, preview URLs and optional GPUs.

Blaxel provides microVM sandboxes for AI agents that resume from standby in about 25 ms.

Hardware-isolated Linux machines that fork in under 200 ms, hibernate and wake with processes intact, on EU bare metal.

Persistent Ubuntu Linux machines in Buddy's cloud with Docker, public endpoints, snapshots and a CLI/SDK.

Hosted microVM sandboxes built on the open-source Apache-2.0 SmolVM core, with suspend, fork and flat hourly sizes.

Anthropic's hosted agent runtime (beta) where Claude runs in per-session cloud Linux containers.

Cloudflare Sandbox SDK runs code in Containers controlled from Workers and Durable Objects.

Coasty is a computer-use agent API with managed Linux or Windows cloud machines and the option to enrol your own device.

A live-fork sandbox cloud for RL post-training that forks running microVMs, memory included, into many rollouts.

Firecracker microVM sandboxes from NodeOps with pause, fork, per-sandbox HTTPS URLs and S3-mounted storage.

A secure runtime for AI agents: Firecracker microVM sandboxes with a per-sandbox security proxy and guardrails.

Persistent Linux VMs (Dedalus Machines) for long-running AI agents, with autosleep and per-second compute billing.

Short-lived Linux microVMs from Deno Deploy, started from JavaScript or Python SDKs, with volumes and snapshots.

Docker's sbx CLI runs coding agents in microVM sandboxes locally, with a cloud option on Docker-managed infrastructure.

A managed platform for coding agents defined in YAML: each session runs Claude Code, Codex or Gemini on an isolated cloud machine.

Persistent hardware-isolated Linux microVMs from Fly.io that sleep when idle and bill only for CPU, memory and storage used.

Freestyle provides full Linux VMs for agents with live forking, pause/resume and HTTPS domains per port.

Kubernetes-native sandbox feature on Google Kubernetes Engine using gVisor, warm pools and open-source CRDs.

Managed sandboxes in Google's Gemini Enterprise Agent Platform: code execution, browser-based computer use, shell and custom containers.

Managed runtime for deploying and scaling agents on Google Cloud, with sessions, Memory Bank and a code execution sandbox.

Cloud sandboxes for AI agents: microVMs with their own kernel, pause/resume, preview URLs, desktop automation, per-second billing.

Huawei Cloud's agent platform with MicroVM-isolated, E2B-compatible sandboxes (AgentSphere) and an AgentArts SDK.

InstaVM runs code for AI agents in microVMs with pause, snapshot, fork and per-second billing.

Incredibuild's sandbox for AI coding agents: microVM machines with credential-injecting gateways, snapshots and automations.

A sandbox runtime that boots KVM-isolated Linux VMs from any OCI image, with hibernate, fork and signed port URLs.

Cloud platform for apps, databases and dev machines, with short-lived hardware-isolated VM sandboxes across ten regions.

Koyeb Sandboxes are ephemeral isolated compute environments on the Koyeb serverless platform.

Managed isolated sandboxes inside LangSmith, with snapshots, service URLs, an auth proxy, and self-hosted and BYOC options.

Firecracker microVM sandboxes for AI-generated code with snapshots, auto-pause, SSH, desktop and an MCP server.

Firecracker microVM sandboxes with snapshots, live fork, persistent volumes and flat hourly sizes, in US and EU regions.

Open-source (Apache-2.0) library and CLI that boots libkrun microVMs locally in under 100 ms, with fork and full-state snapshots.

Microsoft's managed agent platform with a Python Code Interpreter sandbox and hosted-agent containers in per-session VM sandboxes.

Platform for agent products: Firecracker sandboxes, GUI computers, Docker Host deployments, managed data and white-label domains.

Morph Cloud (Infinibranch) offers VM instances you can snapshot, branch, pause and expose over HTTP.

Northflank's microVM sandboxes on Cloud Hypervisor with GPUs, Docker, BYOC and no session limit, billed per second.

Novita AI's usage-billed agent sandbox with pause/resume, snapshots, browser and desktop use, and an enterprise SLA.

Open-source API (Apache 2.0) for running durable agents, with machines from Omnara, your own providers or a local daemon.

Open-source (Apache-2.0) sandbox cloud on Firecracker microVMs, self-hostable or managed in Finland.

Short-lived containers inside the OpenAI API for the Code Interpreter and hosted shell tools, billed per 20-minute session.

OpenComputer (Digger) is a platform for deploying long-running agents as code, each session running on its own Linux machine.

Open-source agent workspace with a cloud sandbox compute service controllable from server-side TypeScript.

Hosted platform for RL training and evaluation environments (ORS), with optional container sandboxes tied to each environment.

Cloud Linux (and Windows) desktop computers for AI agents, controlled via API, CLI, SDKs or MCP.

Open-source (Apache-2.0) KVM microVM sandboxes with snapshot, fork and resume, plus app hosting and managed Postgres.

PPIO's E2B-compatible agent sandbox with pause/resume, snapshots and per-second CPU/RAM billing in RMB, hosted in China.

Prime Intellect Sandboxes run OCI images in hardware-isolated microVMs, built for RL rollouts and agent evals at scale.

Railway Sandboxes are disposable Linux VMs inside Railway environments, with checkpoints, forks and private networking.

Open-source lightweight agent VM runtime (JS/WASM/Python) embedded in your Node backend or hosted as a Rivet Actor.

Runloop provides VM-isolated Devboxes with snapshots and suspend/resume for AI coding agents and evaluation.

Runtime provides Firecracker microVM sandboxes for AI agents billed on active vCPU and reserved memory.

Sail Research's Sailboxes are persistent kernel-isolated Linux VMs for long-running agents.

Managed persistent cloud sandboxes for AI agents with snapshot, fork and memory-based billing.

On-demand Firecracker or Cloud Hypervisor microVMs reached over plain SSH, billed per slot-hour, with memory-snapshot pause.

smol machines runs open-source libkrun microVMs locally, self-hosted or on its managed smol cloud.

Browsers, sandboxes and desktop VMs for AI agents on Cloud Hypervisor microVMs with memory snapshots.

Kubernetes-based code execution runtime for AI agents: one gVisor pod per sandbox, with Kata microVMs as an option. Hosted or self-hosted.

Firecracker microVM sandboxes for agents with pause/resume, memory snapshots and forks, preview URLs, open source and BYOC.

Tangle Network's sandbox for agents: dev containers or microVMs with shell, files, ports, snapshots and per-command GPU leases.

Tencent Cloud's managed sandbox service for AI agents: code, browser and custom sandboxes billed per second, part of Agent Runtime.

Disposable full Linux VMs for AI agents with root, Docker, memory pause and fork, billed per second.

Tensorlake offers MicroVM sandboxes with memory-preserving suspend, snapshots and GPU sandboxes.

Together AI's code sandbox: Docker-image snapshots, per-vCPU and per-GiB billing, and per-port preview URLs, by request access.

Firecracker-based microVM cloud with millisecond cold starts, scale-to-zero, instance snapshots and on-prem option.

Upstash Box is a Docker-container based cloud box with a built-in coding agent, snapshots and SSH.

ByteDance's agent platform (Volcano Engine / BytePlus) with microVM sandbox templates for code, browser and terminal tasks.

Zipbox runs coding agents such as Claude Code and Codex on their own Firecracker microVM computers.