boat vs Docker Cloud Sandboxes

Both give each coding agent its own small Linux VM with Docker inside. boat's machine can run for weeks, has a desktop and browser, and lets you drive the agent inside from outside, while Docker's is the same microVM you already run on your laptop, now in the cloud.

Where boat stands out

Runs as long and as wide as the work

A boat sandbox has no session cap on paid plans, and the $20 plan runs 100 at once. Docker ends a sandbox 24 hours after creation and allows 10 at a time by default, with no published way to ask for more.

A whole machine, screen included

boat exposes /dev/kvm for Android emulators and VMs, and every sandbox has a 60fps Linux desktop with Chromium for computer use. Docker's cloud sandboxes are terminal sessions with Docker inside, and its docs do not offer nested virtualization or a desktop.

Drive agents inside from outside

Claude Code, Codex and five other agents come preinstalled, and you prompt, steer and follow them through one API with structured events. Docker starts agents for you too, but you reach them by attaching to their terminal from the sbx CLI.

The companies and products

boat

boat.dev runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.

You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.

Docker Cloud Sandboxes

Docker Cloud Sandboxes runs Docker's sbx coding-agent microVMs on Docker-managed compute instead of your laptop.

Each sandbox is a microVM with its own Linux kernel and its own Docker Engine, started from the same sbx CLI you use locally, with Claude Code, Codex and other agents ready to run. You can move a sandbox from your laptop to the cloud and back, publish HTTPS ports and SSH in. It launched on September 24, 2026, is billed pay-as-you-go on a personal Docker account, and is built for developers who want their local agent sandboxes to keep going off their machine.

Which use cases each one fits

For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “3rd cheapest of 367” means 2 of the other 366 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.

Use case and its workloadboat: price rankDocker Cloud Sandboxes: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
A software factory runs agents for days and many at once; Docker stops each sandbox at 24 hours and allows 10 at a time by default.
3rd cheapest of 367
$634 a month
280th of 367, with limits
$4,928 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month cannot do it in one Docker session, which ends 24 hours after creation.
5th cheapest of 366
$657 a month
276th of 366, with limits
$5,110 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Docker fits short code runs a little better here: small sandboxes billed by the second, stopped with their memory between runs.
186th of 345, with limits
$2,000 a month
119th of 345, with limits
$233 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Serving your own users needs more than Docker's default 10 concurrent sandboxes, and its plan sits on one personal account.
Cheapest of 361
$209 a month
136th of 361, with limits
$1,628 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
34th of 360, with limits
$2,000 a month
114th of 360, with limits
$7,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
10th cheapest of 364
$200 a month
167th of 364, with limits
$1,400 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
CI that builds Android apps or VM images needs /dev/kvm, which boat exposes and Docker's docs do not offer.
4th cheapest of 377
$86 a month
172nd of 377, with limits
$672 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A dev box that stays on all month needs no session cap; Docker's sandboxes end 24 hours after creation.
18th cheapest of 368
$26 a month
127th of 368, with limits
$204 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Computer-use agents need a screen; boat has a 60fps Linux desktop with Chromium, while Docker's sandboxes are terminal only.
6th cheapest of 369
$200 a month
268th of 369, with limits
$1,400 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
Browser agents need a real browser inside the machine, which boat ships and Docker does not.
7th cheapest of 367
$200 a month
277th of 367, with limits
$700 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
6th cheapest of 346
$90 a month
262nd of 346, with limits
$350 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
71st of 338, with limits
$1,800 a month
190th of 338, with limits
$7,000 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
2nd cheapest of 360
$200 a month
248th of 360, with limits
$350 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Can't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run it

Key features

FeatureboatDocker Cloud Sandboxes
IsolationFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hostsMicroVM with its own Linux kernel; hypervisor not named
Session lengthNo cap on paid plans; you set the time to live1 hour by default, at most 24 hours from creation; resuming starts a new timer
Sandboxes at once100 on the $20 plan, up to 2,000 on higher plans, self-serve10 by default; no published way to raise it
Stop and resumeDisk saved every minute and on stop; resume boots the machine againStop keeps memory and files; resume picks up where it left off
ForkFork a running sandbox with its diskSnapshot a running sandbox with disk or disk and memory, then restore it as a new sandbox
Docker insideYes, with root and systemdYes, its own Docker Engine; agent runs as a non-root user with sudo
Nested virtualizationYes, /dev/kvm for Android emulators and VMsNot documented
Desktop and browser60fps Linux desktop with Chromium and computer useTerminal sessions only
Inbound accessHTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6Public HTTPS URL per published port, not protected by Docker sign-in; not a TCP tunnel; SSH with Docker-issued certificates
Outbound rulesOpen internet, no provider-side allowlistAllow and deny rules by host, with allow-all, balanced and deny-all presets
Coding agentsSeven agents preinstalled, with a prompt, steer and events API to drive them from outsideClaude Code, Codex, Copilot, OpenCode and more, run and attached to from the sbx CLI
Keeping API keys out of the sandboxCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run outCloud proxy sets the auth header for built-in AI services and custom hosts; the sandbox sees a placeholder
Laptop and cloudCloud onlySame microVM and CLI locally or in the cloud; move a sandbox either way
RegionsEU only (Germany, Finland, France)Not published
Compliance and transparencySOC 2 is in progress. We're open about where we stand: live status and data retention policy.No SOC 2 report published
Every feature Battleships tracks (43)
FeatureboatDocker Cloud Sandboxes
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesNo
RootYesYes
SystemdYesNot published
Desktop GUIYesNo
BrowserYesNo
Computer-use APIYesNo
SSHYesYes
Persistent diskYesYes
Pause/resumeYesYes
Automatic snapshotsYesYes
Fork/cloneYesYes
Live fork (no pause)YesYes
Memory forkNoYes
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNoNo
Wake on requestNoNot published
HTTPS preview URLsYesYes
Raw TCP inboundYesNot published
Public IPv4NoNo
Egress allowlistNoYes
Secret proxyYesYes
Secret proxy for any APIYesYes
Preinstalled agentsYesYes
Agent harness APIYesNo
MCP serverNoYes
GPUNoNo
WindowsNoNo
Arm64NoYes
Self-hostingNoNo
BYOCNoNo
Open sourceNoNo
Scoped API keysYesNot published
Spend limitsYesNot published
Usage per sandbox (API)YesNo
Audit logsNoNot published
SSONoYes
SOC 2NoNo
HIPAANoNo
EU data residencyYesNo
Zero data retentionYesNot published

Performance

boat26.69 runs/s
Docker Cloud SandboxesNot measured

There is no comparable measurement for Docker Cloud Sandboxes yet: it launched in September 2026 and is not in the hpc-sandbox-benchmarks runs, and Docker does not say what hardware it uses. boat did 26.69 runs per second on the same Node.js build-and-test benchmark at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Docker Cloud Sandboxes has no published run in this suite yet, so there is no like-for-like number to compare.

Pricing in five scenarios

Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.

Scenarioboat, a monthDocker Cloud Sandboxes, a month
One coding agent, workdays
4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days
$20 · $20/mo$49 · Docker Agentic Platform (pay-as-you-go)
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$204 · Docker Agentic Platform (pay-as-you-go) · with limits
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$317 · $20/mo × 3 seats$2,464 · Docker Agentic Platform (pay-as-you-go) · with limits
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$200 · $100/mo × 2 seats$700 · Docker Agentic Platform (pay-as-you-go) · with limits
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$2,000 · $2000/mo · with limits$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits

boat: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.

Docker Cloud Sandboxes: Docker bills per second for the size you pick, from $0.07 an hour for 1 vCPU / 2 GiB to $1.12 an hour for 16 vCPU / 32 GiB, with no monthly fee. A stopped sandbox costs nothing, and volumes and egress are free; model calls are billed by your model provider.

Limits in those scenarios

Docker ends every sandbox 24 hours after creation, so one agent that never stops does not fit in a single session. Its default quota of 10 concurrent sandboxes is what rules it out for 50 agents in parallel, for sandboxes for your users and for 1,000 short jobs at once, and Docker publishes no way to raise it. boat has no session cap, but its start limits are lower than a 1,000-job burst needs, so even the $2,000 plan queues those starts.

ScenarioboatDocker Cloud Sandboxes
One coding agent, workdaysNone that biteNone that bite
One agent that never stopsNone that bite
  • Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h
50 agents in parallelNone that bite
  • Docker Agentic Platform (pay-as-you-go): max 10 concurrent
Sandboxes for your usersNone that bite
  • Docker Agentic Platform (pay-as-you-go): max 10 concurrent
1,000 short jobs at once
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)
  • Docker Agentic Platform (pay-as-you-go): max 10 concurrent

Which one should you use?

Use Docker Cloud Sandboxes when

you already run agents in sbx on your laptop and want a few of them to keep going in the cloud for up to a day, with memory kept across stops and strict outbound rules.

  • Stop and fork with memory. Useful for agents that pause between steps: a stopped sandbox comes back with its memory and running processes.
  • Outbound rules at the proxy. Teams that must limit where an agent connects can set allow and deny rules by host, enforced outside the VM.
  • The same sandbox on your laptop. If you already run sbx locally, the cloud is the same microVM and CLI, and you can move work between them.

Use boat when

your agents run for days or by the dozen, need Android emulators, a desktop or a browser, or have to be driven from your own app through an API.

  • Runs as long and as wide as the work. An agent on a multi-day task on Docker has to be stopped and resumed by your code before the 24-hour mark, and the eleventh agent waits for a free slot.
  • A whole machine, screen included. An agent that has to test a mobile app, click through a web UI or log into a site cannot do it from a terminal, so on Docker you would add a separate browser service.
  • Drive agents inside from outside. To run agents from your own app or queue on Docker, you write your own wrapper around terminal input and output, then parse the agent's text to know when it is done.

Questions people ask

Is boat cheaper than Docker Cloud Sandboxes?

For one coding agent on workdays, yes: $20 a month on boat against $49 on Docker for the same 4 vCPU / 8 GiB machine. In the other four scenarios Docker does not fit, because of its 24-hour session cap or its default of 10 sandboxes at once.

Can a Docker cloud sandbox run longer than 24 hours?

Not in one session. A Docker cloud sandbox expires after one hour by default, and extensions cannot go past 24 hours from creation; resuming a stopped one starts a new timer. boat has no session cap on paid plans.

How many Docker cloud sandboxes can I run at once?

The default is 10 concurrent and 50 stored per account, and Docker asks you to confirm your limits with them before planning bigger work. boat's $20 plan runs 100 at once, and higher plans go up to 2,000.

Can I run Docker, Android emulators or a browser in each?

Both run Docker inside the sandbox. boat also exposes /dev/kvm for Android emulators and VMs and has a 60fps desktop with Chromium, while Docker's cloud sandboxes are terminal sessions.

Can boat keep a sandbox's memory when it stops, like Docker?

No. boat saves the disk every minute and when the sandbox stops, so files survive, but resuming boots the machine again. Docker keeps memory and files on stop and can fork a running sandbox with its memory.

Is boat SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial

More comparisons