Docker Cloud Sandboxes vs Google Agent Runtime
Docker Cloud Sandboxes gives each coding agent a microVM with its own kernel and Docker Engine, but it ends 24 hours after creation and allows 10 at a time by default. Google Agent Runtime hosts your agent code on Google Cloud and gives it sandboxes that run as an unprivileged user in a locked container, for up to 7 days.
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.
- 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
Google Agent Runtime
Google Agent Runtime is the agent hosting part of Gemini Enterprise Agent Platform on Google Cloud, renamed from Vertex AI Agent Engine in April 2026.
It is a hyperscaler service, not a sandbox company. Agent Runtime deploys agents you build with ADK, LangGraph, LangChain, AG2 or LlamaIndex and bills them only while they work on a turn. Next to it, Agent Sandbox gives those agents a place to run code: a Code Execution sandbox, a shell or custom container sandbox, and a Computer Use browser. All of them run as secure containers inside your Google Cloud project.
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 | Google Agent Runtime: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Docker has root and Docker inside but stops each sandbox at 24 hours and 10 at a time; Google allows 7 days but no sudo or Docker; boat has neither limit. | 280th of 367, with limits $4,928 a month | 295th of 367, with limits $5,801 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Google fits an assistant that lives all week better, since its sandbox lasts up to 7 days and Docker's ends after 24 hours; boat has no session cap on paid plans. | 276th of 366, with limits $5,110 a month | 28th cheapest of 366 $7,519 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 fit short code runs: Docker bills small sandboxes by the second, and Google's Code Execution sandbox is a ready Python interpreter with no network. | 119th of 345, with limits $233 a month | 254th of 345, with limits $275 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's default of 10 sandboxes at once is too few for your users, and Google gives them no public URL; boat serves HTTPS on up to 50 ports per sandbox. | 136th of 361, with limits $1,628 a month | 280th of 361, with limits $1,916 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 | 128th of 360, with limits $8,240 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 | 79th cheapest of 364 $2,060 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 containers runs on Docker, which has its own Docker Engine, and not inside Google's unprivileged sandboxes; boat adds /dev/kvm for Android and VM images. | 172nd of 377, with limits $672 a month | 98th cheapest of 377 $989 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Docker gives you SSH but ends the sandbox after 24 hours, and Google has no SSH at all; boat gives you SSH, a desktop and no session cap. | 127th of 368, with limits $204 a month | 311th of 368, with limits $241 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 Google offers a browser with a VNC view and a click and type API, while Docker is terminal only; boat streams a full 60fps desktop with Chromium. | 268th of 369, with limits $1,400 a month | 283rd of 369, with limits $1,648 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 Google ships a real Chromium you can drive over CDP and Docker does not, so browser agents fit Google better; boat ships Chromium on every sandbox. | 277th of 367, with limits $700 a month | 102nd of 367, with limits $824 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 | 53rd cheapest of 346 $515 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 | 210th of 338, with limits $8,240 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 | 248th of 360, with limits $350 a month | 260th of 360, with limits $412 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 | Google Agent Runtime | boat |
|---|---|---|---|
| Isolation | MicroVM with its own Linux kernel; hypervisor not named | Secure container sandboxing inside your Google Cloud project | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root and Docker inside | Its own Docker Engine; agent runs as a non-root user with sudo | Runs as appuser with no sudo; images must not need root; no Docker documented | Root, systemd and Docker on every machine |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| How long a sandbox lives | 1 hour by default, at most 24 hours from creation | TTL of up to 7 days for a custom container, 14 days for Code Execution | No session cap on paid plans; you set the time to live |
| Sandboxes at once | 10 by default; no published way to raise it | Not published; set by your Google Cloud project quota | 100 on the $20 plan, up to 2,000 on higher plans, self-serve |
| Stop, snapshot and fork | Stop keeps memory and files; snapshot a running sandbox with its memory and restore it as a new one | Pause keeps files; snapshots keep memory and files, and many sandboxes can start from one | Disk saved every minute and on stop; fork a running sandbox with its disk; no memory snapshots |
| Shell access | SSH with Docker-issued certificates, plus the sbx CLI | execute_bash() API calls; each command runs in a new shell; no SSH | SSH, plus an API for commands |
| Desktop and browser | Terminal sessions only | A browser in a container with a VNC live view, a click and type API, and CDP | 60fps Linux desktop with Chromium and computer use |
| Inbound access | Public HTTPS URL per published port, not protected by Docker sign-in; not a TCP tunnel | Through Google's API or a private endpoint in your VPC; no public URL documented | 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 at a proxy, with allow-all, balanced and deny-all presets | Off unless the template turns it on; can route through your VPC with Cloud NAT, a static IP or Cloud NGFW | Open internet, no provider-side allowlist |
| Coding agents | Claude Code, Codex, Copilot, OpenCode and more, attached to from the sbx CLI | Managed Agents API (Preview) runs Google's Antigravity harness | Seven agents preinstalled, with a prompt, steer and events API to drive them from outside |
| Keeping API keys out of the sandbox | Cloud proxy sets the auth header for built-in AI services and custom hosts | You provision and scope the credentials the agent uses | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Hosting agent code and laptop use | Same microVM and CLI on your laptop or in the cloud; move a sandbox either way | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | Cloud only; you run your own agent loop inside a sandbox |
| Regions | Not published | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Docker Cloud Sandboxes | Google Agent Runtime | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | No | 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 | No | No | No |
| Wake on request | Not published | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | Not published | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | No | 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 | Yes | 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 | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | No | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Docker Cloud Sandboxes or Google Agent Runtime: neither was part of the hpc-sandbox-benchmarks runs. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run of 2026-09-29, 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 and Google Agent Runtime 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 | Google Agent Runtime, 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) | $73 · Pay as you go | $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 | $301 · Pay as you go | $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 | $3,626 · 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 | $700 · Docker Agentic Platform (pay-as-you-go) · with limits | $1,030 · Pay as you go | $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 | $2,060 · Pay as you go | $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.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, with the first 50 vCPU-hours and 100 GiB-hours free each month. Sandboxes are billed while they exist, and disk, egress and paused rates are not published.
Google Agent Runtime: Plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Docker's default of 10 concurrent sandboxes rules it out for 50 agents in parallel, sandboxes for your users and 1,000 short jobs at once, and its 24-hour cap means one agent that never stops does not fit. Google fits those rows except the 50-agent fleet, which needs Docker inside, and every Google row leaves disk and egress unpriced. boat fits every row but the 1,000-job burst, where its start limits queue the jobs.
| Scenario | Docker Cloud Sandboxes | Google Agent Runtime | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
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 Docker inside, SSH and memory kept across stops.
- Docker and sudo inside. Agents that run docker compose or install packages get their own Docker Engine and sudo, which Google's sandboxes do not allow.
- 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 between them.
- SSH and public ports. Developers can SSH into a sandbox and open a public HTTPS URL for a port, which Google's sandboxes do not document.
Use Google Agent Runtime when
you build agents with ADK or LangGraph on Google Cloud and want them hosted inside your own project, network rules and regions, with short code or browser runs in a locked sandbox.
- A managed home for your agent code. Teams building with ADK or LangGraph get their agents hosted, scaled and not billed for idle time between turns.
- Longer lives and a browser. A sandbox can live up to 7 days, and the Computer Use sandbox gives agents a real browser with a live view.
- Inside your Google Cloud network. Agents can stay in your project, with egress off by default and routed through your own firewall, in 23 locations.
Where boat fits
Both products give an agent a place to work, but each takes something away: Docker takes time and width, Google takes root and the open network. If your agents run for days, by the dozen, need a screen or have to show what they built, boat gives each one a full VM with none of those gaps.
No session cap, no 10-sandbox ceiling
Docker ends a sandbox 24 hours after creation and runs 10 at a time; Google deletes one after 7 days. On both, your code has to stop, recreate and restore long agents. boat has no cap on paid plans and runs 100 at once on $20.
A whole machine, screen included
Google has no root or Docker, Docker has no desktop, and neither documents /dev/kvm. So an agent cannot both build containers and click through an app. boat has root, Docker, /dev/kvm and a 60fps desktop with Chromium on every VM.
Drive agents inside from outside
On Docker you attach to an agent's terminal and parse its text; Google only runs its own Antigravity harness. boat preinstalls Claude Code, Codex and five more, with a prompt, steer and events API, and a credentials proxy that keeps keys out.
Use boat when your agents run for days or by the dozen, need root, Docker, /dev/kvm, a desktop or public URLs, or have to be driven from your own app through an API. Compare it one to one: boat vs Docker Cloud Sandboxes and boat vs Google Agent Runtime.
Questions people ask
Is Docker Cloud Sandboxes cheaper than Google Agent Runtime?
In our scenarios, yes: one coding agent on workdays comes to $49 a month on Docker against $73 on Google, and sandboxes for your users $700 against $1,030, though Docker's 10-sandbox default does not fit that one. boat comes to $20 and $200 for the same two.
Which is faster?
We cannot say: neither Docker Cloud Sandboxes nor Google Agent Runtime has a published benchmark we can compare. boat did 26.69 runs per second on a Node.js build-and-test benchmark at 4 vCPU / 8 GB.
Can Google Agent Runtime run Docker like Docker Cloud Sandboxes?
No. Google's shell sandbox runs commands as the unprivileged user appuser with no sudo, and custom images must not need root. Each Docker cloud sandbox has its own Docker Engine, and boat runs Docker with root and systemd.
How long can a sandbox run on each?
A Docker cloud sandbox lasts 1 hour by default and at most 24 hours from creation. A Google sandbox has a TTL of up to 7 days for a custom container and 14 days for Code Execution. boat has no session cap on paid plans.
Is Google Agent Runtime the same as Vertex AI Agent Engine?
Yes. Google renamed Vertex AI Agent Engine to Agent Runtime in April 2026, as part of Gemini Enterprise Agent Platform. Its code, shell and browser sandboxes are a separate part called Agent Sandbox.
Can either show a desktop or a browser?
Docker's cloud sandboxes are terminal sessions only. Google's Computer Use sandbox runs a browser with a VNC live view and CDP for Playwright. boat streams a 60fps Linux desktop with Chromium on every sandbox.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Docker Cloud Sandboxes
- boat vs Google Agent Runtime
- E2B vs Docker Cloud Sandboxes
- Daytona vs Docker Cloud Sandboxes
- Modal vs Docker Cloud Sandboxes
- Vercel Sandbox vs Docker Cloud Sandboxes
- Cloudflare Sandbox vs Docker Cloud Sandboxes
- Blaxel vs Docker Cloud Sandboxes
- Runloop vs Docker Cloud Sandboxes
- Tensorlake vs Docker Cloud Sandboxes
- Morph Cloud vs Docker Cloud Sandboxes
- CodeSandbox SDK vs Docker Cloud Sandboxes