Freestyle vs Docker Cloud Sandboxes
Freestyle gives each agent a full KVM virtual machine that can run as long as you like, pause with its memory and wake on the next request. Docker Cloud Sandboxes runs the same sbx microVM you use on your laptop in the cloud, for up to 24 hours a session and 10 at a time by default.
The companies and products
Freestyle
Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.
Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.
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.
- Launched
- September 24, 2026
- Session length
- 1 hour by default, extendable to 24 hours from creation
- Default quota
- 10 concurrent and 50 stored sandboxes per account
- Regions
- Not published
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. “40th cheapest of 345” means 39 of the other 344 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 | Freestyle: price rank | Docker Cloud Sandboxes: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory runs many agents for days; Docker stops each sandbox at 24 hours and allows 10 at once, while Freestyle has no cap but its docs send sustained heavy CPU work elsewhere. | 241st of 367, with limits $3,311 a month | 280th of 367, with limits $4,928 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month fits on Freestyle, but not in one Docker session, which ends 24 hours after creation. | 263rd of 366, with limits $4,195 a month | 276th of 366, with limits $5,110 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 Both suit short code runs: Freestyle wakes a paused VM on the next request, and Docker stops small sandboxes with their memory and bills nothing while they are stopped. | 40th cheapest of 345 $482 a month | 119th of 345, with limits $233 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 Freestyle ranks 16th here because Pro runs 400 VMs at once and wakes each on request, while Docker's default of 10 concurrent sandboxes is too few for your users. | 16th cheapest of 361 $1,358 a month | 136th of 361, with limits $1,628 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 | 107th of 360, with limits $6,600 a month | 114th of 360, with limits $7,000 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 Evals run many sandboxes side by side, which Freestyle Pro allows up to 400 of and Docker caps at 10 by default. | 53rd cheapest of 364 $1,046 a month | 167th of 364, with limits $1,400 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 CI that builds Android apps or VM images needs /dev/kvm, which Freestyle and boat expose and Docker's docs do not offer. | 168th of 377, with limits $625 a month | 172nd of 377, with limits $672 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 needs no session cap, which Freestyle and boat give and Docker does not. | 98th cheapest of 368 $151 a month | 127th of 368, with limits $204 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 Computer-use agents need a screen: boat streams a 60fps desktop, Freestyle has guides to install one yourself, and Docker's sandboxes are terminal only. | 234th of 369, with limits $940 a month | 268th of 369, with limits $1,400 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 | 257th of 367, with limits $482 a month | 277th of 367, with limits $700 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 | 278th of 346, with limits $482 a month | 262nd of 346, with limits $350 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 | 183rd of 338, with limits $6,560 a month | 190th of 338, with limits $7,000 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 | 272nd of 360, with limits $482 a month | 248th of 360, with limits $350 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 | Freestyle | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| Isolation | Full KVM VM with its own kernel on bare metal servers | MicroVM with its own Linux kernel; hypervisor not named | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| CPU benchmark (4 vCPU / 8 GB) | 9.64 runs/s | Not measured | 26.69 runs/s |
| Session length | No provider cap; optional run limits and idle timeouts you set | 1 hour by default, at most 24 hours from creation | No cap on paid plans; you set the time to live |
| Sandboxes at once | 10 on Free, 40 on Hobby, 400 on Pro | 10 by default; no published way to raise it | 100 on the $20 plan, up to 2,000 on higher plans, self-serve |
| Biggest machine | Up to 32 vCPU / 64 GiB on Pro, 64 / 128 with custom limits | Up to 16 vCPU / 32 GiB, amd64 or arm64 by account | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Pause and resume | Pause saves memory and disk; the same processes resume | Stop keeps memory and files; resume picks up where it left off | Disk saved every minute and on stop; resume boots the machine again |
| Wake on request | A VM paused by idle timeout resumes on the next traffic that reaches it | Not documented | No; a stopped sandbox is started by API |
| Fork | Clone a running VM without pausing it; snapshots capture memory and disk | Snapshot a running sandbox with disk or memory, then restore it as a new one | Fork a running sandbox with its disk |
| Docker and nested virtualization | Docker from boot, systemd as pid 1, full KVM support | Its own Docker Engine; nested virtualization not documented | Docker, root and systemd, with /dev/kvm for Android emulators and VMs |
| Desktop and browser | Guides to install GNOME or Xvfb, VNC and Chromium yourself | Terminal sessions only | Linux desktop streamed at 60fps, Chromium and computer use built in |
| Coding agents | claude, codex, opencode and openclaw preinstalled, driven through exec or a terminal | Claude Code, Codex, Copilot, OpenCode and more, attached to from the sbx CLI | Seven agents preinstalled, with a prompt, steer and events API to drive them from outside |
| Network rules and inbound access | Default-deny firewall by IP, VM, VPC or domain; HTTPS on your own domain with forward auth | Allow and deny rules by host at a proxy; public HTTPS URL per port, not a TCP tunnel | Open internet outbound; HTTPS URLs for up to 50 ports, token-protected by default, and raw TCP |
| Laptop and cloud | Cloud only | Same microVM and CLI locally or in the cloud; move a sandbox either way | Cloud only |
| Idle cost and regions | A paused VM bills for its storage; regions not listed, docs name San Jose, US | A stopped sandbox costs nothing; regions not published | A stopped sandbox costs nothing and keeps its disk; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Freestyle | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | No | Yes |
| Computer-use API | No | No | 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 | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | Not published | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Yes | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | No | Yes | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | No | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Not published | No | No |
| HIPAA | Not published | No | No |
| EU data residency | No | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, Freestyle did 9.64 runs per second and boat did 26.69, so boat finished about 2.8 times as much CPU work. Docker Cloud Sandboxes has no comparable measurement yet: it launched in September 2026 and Docker does not say what hardware it uses. None of this measures start time, where Freestyle advertises about 65 ms.
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.
| Scenario | Freestyle, a month | Docker Cloud Sandboxes, 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 | $27 · Free | $49 · Docker Agentic Platform (pay-as-you-go) | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $159 · Free | $204 · Docker Agentic Platform (pay-as-you-go) · with limits | $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 | $2,139 · Pro | $2,464 · Docker Agentic Platform (pay-as-you-go) · with limits | $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 | $581 · Pro | $700 · Docker Agentic Platform (pay-as-you-go) · 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 | $1,305 · Pro · with limits | $1,400 · Docker Agentic Platform (pay-as-you-go) · with limits | $2,000 · $2000/mo · with limits |
Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. On Free those allowances are hard stops; Hobby and Pro set a $50 or $500 monthly minimum that counts as usage.
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.
Docker Cloud Sandboxes: 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, and its default of 10 at once rules it out for 50 agents in parallel, for sandboxes for your users and for 1,000 short jobs at once. Freestyle fits all of those except the burst, because Pro caps at 400 concurrent VMs. Freestyle has no idle timeout by default, so a VM bills until you pause it, and on Free the monthly allowances are hard stops. 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.
| Scenario | Freestyle | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite | None that bite | None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users | None that bite |
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Freestyle when
your agents run for days or by the hundred, when VMs must sleep and wake on the next request with their memory, or when you need tight network rules or more than 16 vCPU.
- No session cap, hundreds at once. For agents that run for days or by the hundred: no provider time limit, and Pro runs 400 VMs at once.
- Wake on request and strict networking. For VMs that sleep between requests: they wake on the next traffic, behind a default-deny firewall you open rule by rule.
- Bigger machines. For heavy single jobs: Pro VMs go up to 32 vCPU / 64 GiB, and custom limits reach 64 / 128.
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, paying nothing while they are stopped.
- 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.
- Nothing to pay when stopped. For a few agents that work in bursts: no monthly fee, and a stopped sandbox keeps its memory and costs nothing.
- 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.
Where boat fits
Freestyle and Docker both give agents a Linux machine with Docker inside, and both shine when sandboxes pause with their memory. If your agents instead do long, heavy work, need a screen or a browser, or have to be driven from your own app, boat gives them a full VM on faster CPUs with those parts built in.
A desktop and a browser, ready
Every boat sandbox streams a Linux desktop at 60fps with Chromium and computer use. Docker's cloud sandboxes are terminal only, and on Freestyle you install GNOME or Xvfb, VNC and Chromium yourself and keep them in your snapshot.
Agents you drive from outside
boat's API prompts, steers and follows the agents inside with structured events. Freestyle starts them through exec or a terminal, Docker through its sbx CLI, so you wrap terminal output and guess when the agent is done.
A whole machine on fast CPUs
boat did 26.69 runs per second on the CPU benchmark against 9.64 for Freestyle, whose docs send sustained heavy CPU work elsewhere. Docker is unmeasured and does not document /dev/kvm, which boat exposes for Android emulators.
Use boat when your agents do real work for hours or weeks: builds, tests, Docker, emulators, a desktop and a browser, on fast CPUs, with an API to drive the agents inside from outside. Compare it one to one: boat vs Freestyle and boat vs Docker Cloud Sandboxes.
Questions people ask
Is Freestyle cheaper than Docker Cloud Sandboxes?
In our scenarios, yes. One coding agent on workdays costs $27 a month on Freestyle against $49 on Docker, and one agent running all month is $159 on Freestyle while Docker cannot run it in one session. boat is $20 and $26 for the same two.
Which is faster, Freestyle or Docker Cloud Sandboxes?
Only Freestyle has been measured: 9.64 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB. Docker Cloud Sandboxes is new and not in those runs. boat did 26.69 on the same test.
Can a Docker cloud sandbox run longer than 24 hours?
Not in one session. It expires after one hour by default, and extensions cannot go past 24 hours from creation. Freestyle sets no session cap, and boat has none on paid plans.
How many sandboxes can I run at once on each?
Docker allows 10 concurrent sandboxes per account by default and publishes no way to raise it. Freestyle allows 10 on Free, 40 on Hobby and 400 on Pro. boat's $20 plan runs 100 at once, and higher plans go up to 2,000.
Can both run Docker and Android emulators?
Both run Docker inside the sandbox. Freestyle also has full KVM support for emulators and VMs, while Docker's docs do not offer nested virtualization. boat exposes /dev/kvm too.
Do both keep memory when a sandbox pauses?
Yes. Freestyle pauses a VM with its memory and can wake it on the next request, and Docker keeps memory and files when a sandbox stops. boat saves the disk every minute and on stop, but resuming boots the machine again.
Try boat
Install the CLI, then run boat new.
7-day free trial