Docker Cloud Sandboxes vs Agent 37

Docker Cloud Sandboxes puts the same microVM you run on your laptop into the cloud, with Docker inside, for up to 24 hours at a time. Agent 37 keeps one lighter gVisor sandbox per user running with no time limit, putting it to sleep when idle and waking it on the next message.

The companies and products

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.

Isolation: MicroVM per sandbox with its own Linux kernel and its own Docker Engine
Launched: September 24, 2026
Machine sizes: 1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, CPU only, amd64 or arm64 by account
Session length: 1 hour by default, extendable to 24 hours from creation
Default quota: 10 concurrent and 50 stored sandboxes per account
Account: Pay-as-you-go plan on a personal Docker account, even inside an organization
Regions: Not published

Agent 37

Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.

You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor; a VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.

Isolation: gVisor by default; opt-in full VM type with its own kernel and KVM
Where it runs: Dedicated servers in the United States
Billing: Prepaid wallet, metered per minute, no plan fee or seat charge
Instance types: Default (shared), Performance (dedicated cores), VM
Compliance: SOC 2 Type I, Type II in progress
Company: Y Combinator company based in New York

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. “280th cheapest of 367” means 279 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 workload	Docker Cloud Sandboxes: price rank	Agent 37: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Docker gives every sandbox its own Docker Engine but stops it at 24 hours and runs 10 at once; Agent 37 needs its VM type for Docker, and boat has Docker, systemd and no session cap in every sandbox.	280th of 367, with limits $4,928 a month	2nd cheapest of 367 $551 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 is built for an assistant that lives on its machine all month and sleeps when idle; a Docker session ends 24 hours after creation.	276th of 366, with limits $5,110 a month	Cheapest of 366 $279 a month	5th cheapest of 366 $657 a month
Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Agent 37's small default sandboxes suit short code runs best here; Docker's are billed by the second but cost more per hour, and boat's start limits make big bursts a poor fit.	119th of 345, with limits $233 a month	Cheapest of 345 $22 a month	186th of 345, with limits $2,000 a month
Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Docker allows 10 sandboxes at once by default and Agent 37 stops at 200 self-serve instances counting sleeping ones; boat plans go up to 2,000 at once.	136th of 361, with limits $1,628 a month	30th of 361, with limits $79 a month	Cheapest of 361 $209 a month
RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month	114th of 360, with limits $7,000 a month	6th of 360, with limits $363 a month	34th of 360, with limits $2,000 a month
Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month	167th of 364, with limits $1,400 a month	90th of 364, with limits $58 a month	10th cheapest of 364 $200 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Agent 37 and boat both keep up with CI here; Docker's 10 concurrent sandboxes hold a busy queue back, and only boat and Agent 37's VM type expose /dev/kvm for Android builds.	172nd of 377, with limits $672 a month	2nd cheapest of 377 $84 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that stays on all month fits Agent 37 and boat, which have no session cap; Docker's sandboxes end 24 hours after creation.	127th of 368, with limits $204 a month	3rd cheapest of 368 $12 a month	18th cheapest of 368 $26 a month
Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Docker's cloud sandboxes are terminal only; Agent 37 adds a noVNC desktop through a template build, and boat streams a 60fps desktop with Chromium in every sandbox.	268th of 369, with limits $1,400 a month	Cheapest of 369 $53 a month	6th cheapest of 369 $200 a month
Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month	277th of 367, with limits $700 a month	48th of 367, with limits $29 a month	7th cheapest of 367 $200 a month
Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month	262nd of 346, with limits $350 a month	Cheapest of 346 $32 a month	6th cheapest of 346 $90 a month
Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month	190th of 338, with limits $7,000 a month	36th of 338, with limits $648 a month	71st of 338, with limits $1,800 a month
Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month Docker can snapshot a running sandbox with its memory and boat can fork one that is running, which helps try many paths at once; Agent 37 has no fork.	248th of 360, with limits $350 a month	Cheapest of 360 $43 a month	2nd cheapest of 360 $200 a month
GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month	Can't run it	Can't run it	Can't run it
macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month	Can't run it	Can't run it	Can't run it

Key features

Feature	Docker Cloud Sandboxes	Agent 37	boat
Isolation	MicroVM per sandbox with its own Linux kernel; hypervisor not named	gVisor by default; full VM with its own kernel as an opt-in instance type	Every sandbox is a full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker inside	Yes, its own Docker Engine in every sandbox; the agent runs as a non-root user with sudo	Only on the VM type, at 2.5x the default compute rate, and with no init system even there	Yes, in every sandbox, with root and systemd
Session length	1 hour by default, at most 24 hours from creation	No documented limit; runs until you stop it or it auto-sleeps	No cap on paid plans; you set the time to live
Sandboxes at once	10 concurrent and 50 stored by default; no published way to raise it	1 before a top-up, 10 after, 50 at $100 and 200 at $250 of lifetime top-ups, counting sleeping and stopped ones	100 on the $20 plan, up to 2,000 on higher plans, self-serve
Stop, sleep and resume	Stop keeps memory and files; resume picks up where it left off	Opt-in auto-sleep after a quiet period (default 15 minutes) keeps memory and wakes on the next request	Disk saved every minute and on stop; resume boots the machine again
Fork	Snapshot a running sandbox with disk or disk and memory, then restore it as a new sandbox	No fork; daily backups plus one on-demand backup, restored in place only	Fork a running sandbox with its disk; named snapshots as shareable templates
Nested virtualization	Not documented	/dev/kvm on the VM type, with a ready Android template	/dev/kvm in every sandbox for Android emulators and VMs
Desktop and browser	Terminal sessions only	noVNC desktop through a template build or the Ubuntu VM template	60fps Linux desktop with Chromium and computer use in every sandbox
Inbound access	Public HTTPS URL per published port; not a TCP tunnel; SSH with Docker-issued certificates	HTTPS URL per port, signed URLs, custom domains; no public IP, SSH through a WebSocket tunnel	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Outbound rules	Allow and deny rules by host, with allow-all, balanced and deny-all presets	Open internet; no outbound allowlist documented	Open internet, no provider-side allowlist
Coding agents	Claude Code, Codex, Copilot, OpenCode and more, attached to from the sbx CLI	Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API per instance	Seven agents preinstalled, with a prompt, steer and events API to drive agents inside from outside
Keeping API keys out of the sandbox	Cloud proxy sets the auth header for built-in AI services and custom hosts	Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Laptop and cloud	Same microVM and CLI locally or in the cloud; move a sandbox either way	Cloud only	Cloud only
Regions	Not published	Dedicated servers in the United States	EU only (Germany, Finland, France), EU data residency

Every feature Battleships tracks (43)

Feature	Docker Cloud Sandboxes	Agent 37	boat
Full VM (own kernel)	Yes	No	Yes
Docker inside	Yes	No	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	Yes	Yes
Browser	No	Yes	Yes
Computer-use API	No	Yes	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	Yes	Yes	Yes
Fork/clone	Yes	Yes	Yes
Live fork (no pause)	Yes	Yes	Yes
Memory fork	Yes	No	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	No	Yes	No
Wake on request	Not published	Yes	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	Not published	Not published	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	No	No
Secret proxy	Yes	Yes	Yes
Secret proxy for any API	Yes	No	Yes
Preinstalled agents	Yes	Yes	Yes
Agent harness API	No	Yes	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	Yes	No	No
Self-hosting	No	No	No
BYOC	No	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Not published	Yes	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Not published	Not published	No
SSO	Yes	No	No
SOC 2	No	Yes	No
HIPAA	No	No	No
EU data residency	No	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

Docker Cloud SandboxesNot measured

Agent 37Not measured

boat26.69 runs/s

Neither Docker Cloud Sandboxes nor Agent 37 has a comparable CPU measurement: neither is in the hpc-sandbox-benchmarks runs. boat did 26.69 runs per second on that Node.js build-and-test benchmark at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Agent 37 says its default instances share host resources, and sells a Performance type on dedicated cores.

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 and Agent 37 have 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.

Scenario	Docker Cloud Sandboxes, a month	Agent 37, a month	boat, 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	$49 · Docker Agentic Platform (pay-as-you-go)	$6 · Wallet (any top-up)	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$204 · Docker Agentic Platform (pay-as-you-go) · with limits	$12 · Wallet (any top-up)	$26 · $20/mo
50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside	$2,464 · Docker Agentic Platform (pay-as-you-go) · with limits	$329 · Wallet ($100 lifetime top-ups)	$317 · $20/mo × 3 seats
Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once	$700 · Docker Agentic Platform (pay-as-you-go) · with limits	$33 · Wallet ($250 lifetime top-ups) · with limits	$200 · $100/mo × 2 seats
1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month	$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits	$73 · Wallet ($250 lifetime top-ups) · with limits	$2,000 · $2000/mo · with limits

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.

Agent 37: A prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while stopped or asleep. Performance compute costs 4x and VM compute 2.5x the default rate.

Agent 37: 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.

Limits in those scenarios

Docker ends every sandbox 24 hours after creation, so one agent that never stops does not fit, and its default of 10 at once rules it out for 50 agents in parallel, sandboxes for your users and 1,000 short jobs at once. Agent 37 fits the first three scenarios, with 50 agents priced on its VM type because they need Docker, but its 200-instance self-serve cap stops it for your users and the burst. boat fits every scenario but the burst, where its start limits queue the jobs.

Scenario	Docker Cloud Sandboxes	Agent 37	boat
One coding agent, workdays	None that bite	egress price not published	None that bite
One agent that never stops	Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h	egress price not published	None that bite
50 agents in parallel	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	egress price not published	None that bite
Sandboxes for your users	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	max 200 concurrent egress price not published	None that bite
1,000 short jobs at once	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	max 200 concurrent shared vCPUs on this tier: heavy, sustained CPU use can be slowed by other tenants egress price not published	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)

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. For agents that pause between steps: a stopped sandbox keeps its memory, and a running one can be snapshotted and restored as a new one.
Outbound rules at the proxy. For teams that must limit where an agent connects: 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 a sandbox either way.

Use Agent 37 when

you host one mostly idle assistant per customer in the US that should run with no time limit, sleep with its memory kept and wake on the next message.

Sleeps when idle and keeps its memory. For assistants that sit idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
No session time limit. For agents that live on one machine for weeks: an instance runs until you stop it, with no 24-hour cutoff.
Bring a Dockerfile, pick dedicated cores. Agent 37 builds templates from your own Docker image, and sells a Performance type on dedicated cores.

Where boat fits

Look at boat when your agents do real work for hours or days: installs, builds, Docker, emulators and browsers, many at once. Docker Cloud Sandboxes stops at 24 hours and 10 at a time, and Agent 37 needs its pricier VM type before Docker runs. boat gives every sandbox a full VM with no session cap on paid plans.

A whole machine in every sandbox

Docker has Docker inside but no documented /dev/kvm or init. Agent 37's default type cannot run Docker; its VM type can, at 2.5x compute and with no systemd. boat has Docker, systemd and /dev/kvm everywhere.

Runs as long and as wide as the work

Docker ends a sandbox 24 hours after creation and runs 10 at once. Agent 37's cap counts sleeping instances and stops at 200 self-serve. boat has no session cap, runs 100 on the $20 plan and forks running sandboxes.

A screen and an API to drive it

Docker's sandboxes are terminal only, reached by attaching from the sbx CLI. Agent 37's desktop is a noVNC template build. boat streams a 60fps desktop with Chromium and drives agents inside from outside through a prompt, steer and events API.

Use boat when your agents run for days or by the dozen and need Docker, systemd, Android emulators, a desktop or a browser on a full VM, driven from your own app through an API. Compare it one to one: boat vs Docker Cloud Sandboxes and boat vs Agent 37.

Questions people ask

Is Docker Cloud Sandboxes cheaper than Agent 37?

No. For one coding agent on workdays at 4 vCPU / 8 GiB, Docker comes to $49 a month and Agent 37 to $6, with boat at $20. For 50 agents in parallel, which need Docker, Agent 37 uses its VM type at $329 a month, boat comes to $317, and Docker does not fit its default of 10 at once.

Which is faster, Docker Cloud Sandboxes or Agent 37?

There is no comparable measurement for either: neither is in the hpc-sandbox-benchmarks runs. boat did 26.69 runs per second there at 4 vCPU / 8 GB. Agent 37's default instances share host resources, and its Performance type runs on dedicated cores.

Can Agent 37 run Docker like Docker Cloud Sandboxes?

Only on its VM type, which bills compute at 2.5x the default rate; the default gVisor type cannot run a Docker daemon. Every Docker cloud sandbox has its own Docker Engine, and so does every boat sandbox, with systemd as well.

How long can a sandbox run on each?

A Docker cloud sandbox runs 1 hour by default and at most 24 hours from creation. Agent 37 documents no time limit: an instance runs until you stop it or it auto-sleeps. boat has no session cap on paid plans.

Which one keeps memory when the sandbox stops?

Both do. Docker keeps memory and files on stop and can snapshot a running sandbox with its memory; Agent 37 checkpoints memory when an instance auto-sleeps. boat keeps the disk, saved every minute, but reboots on resume.

Where do Docker Cloud Sandboxes and Agent 37 run?

Docker does not publish its regions. Agent 37 runs on dedicated servers in the United States. boat runs only in the EU, in Germany, Finland and France, with EU data residency.

Try boat

Install the CLI, then run boat new.

7-day free trial