boat vs Google Agent Runtime
Google Agent Runtime, once called Vertex AI Agent Engine, hosts your agent code on Google Cloud and adds sandboxes that run as an unprivileged user in a locked container. boat gives every agent a full VM with root, Docker, a desktop and coding agents built in, and it costs less in all five scenarios below.
Where boat stands out
Root, Docker and a real kernel
On boat every sandbox is a VM with its own kernel, with root, systemd, Docker and /dev/kvm ready. Google's shell sandbox runs commands as the unprivileged user appuser with no sudo, and custom images must not need root. So apt installs, Docker builds and Android emulators work on boat and not inside a Google sandbox.
Public URLs for what agents build
A boat sandbox can serve HTTPS on up to 50 ports with token protection, accept raw TCP and get its own IP address. A Google sandbox is reached through Google's API or a private endpoint inside your own VPC, and its docs describe no public URL. On boat you can SSH in too.
Coding agents you drive from outside
boat ships Claude Code, Codex, pi, OpenCode and other agents inside each sandbox, and you drive them from outside with a prompt, steer and events API. Google's Managed Agents API is in Preview and runs its own Antigravity harness. boat's credentials proxy also keeps real AI keys out of the sandbox and can switch to another account when one runs out of credits.
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.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
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. “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 workload | boat: price rank | Google Agent Runtime: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Google's sandboxes run without root or Docker, so installs that need sudo, docker compose stacks and emulators do not run there; boat has all of them on every VM. | 3rd cheapest of 367 $634 a month | 295th of 367, with limits $5,801 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB A Google sandbox is deleted when its TTL runs out (7 days at most for a custom container), so a long-lived assistant needs restarts; a boat VM has no session cap on paid plans. | 5th cheapest of 366 $657 a month | 28th cheapest of 366 $7,519 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month This is where Google fits best: its Code Execution sandbox is a ready Python interpreter with no network, and new sandboxes start without a plan. | 186th of 345, with limits $2,000 a month | 254th of 345, with limits $275 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Your users get a shell through Google's API but no public URL for what they build, while on boat each sandbox can serve HTTPS on up to 50 ports. | Cheapest of 361 $209 a month | 280th of 361, with limits $1,916 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 | 128th of 360, with limits $8,240 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 | 79th cheapest of 364 $2,060 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build containers need Docker, which Google's unprivileged sandboxes do not offer; boat runs Docker and systemd on every VM. | 4th cheapest of 377 $86 a month | 98th cheapest of 377 $989 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Google has no SSH into a sandbox and each command runs in a new shell, so it does not work as a dev box you log into; boat gives you SSH and a desktop. | 18th cheapest of 368 $26 a month | 311th of 368, with limits $241 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Google gives you only a browser, with a VNC view, a click and type API and CDP, so desktop apps are out of reach; boat streams a full 60fps desktop with Chromium. | 6th cheapest of 369 $200 a month | 283rd of 369, with limits $1,648 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both run a real Chromium you can drive over CDP with Playwright; Google keeps outbound internet off unless the template turns it on. | 7th cheapest of 367 $200 a month | 102nd of 367, with limits $824 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 | 53rd cheapest of 346 $515 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 | 210th of 338, with limits $8,240 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 | 260th of 360, with limits $412 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 |
| 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 |
Key features
| Feature | boat | Google Agent Runtime |
|---|---|---|
| Isolation | Every sandbox is a full VM with its own kernel | Secure container sandboxing inside Google Cloud |
| Root, Docker and nested virtualization | Root, systemd, Docker and /dev/kvm on every machine | Runs as appuser with no sudo; images must not need root; no Docker or /dev/kvm documented |
| Shell access | SSH, plus an API for commands | execute_bash() API calls; each command runs in a new shell; no SSH |
| Desktop and computer use | 60fps desktop and Chromium, computer use and browser control, embeddable stream | A browser in a container with a VNC live view, a click, type and screenshot API, and CDP for Playwright |
| Files after a stop | Snapshots every minute and on stop; a stopped sandbox costs nothing | Pause keeps the file system and costs less (rate not published); the sandbox is deleted when its TTL ends |
| Memory snapshots and branching | Fork a running sandbox; resume reboots from disk (no memory snapshots) | Snapshots keep memory and files; start many sandboxes from one snapshot (same image and architecture) |
| How long a sandbox lives | No session cap on paid plans | TTL of up to 7 days for a custom container and 14 days for Code Execution |
| Reaching the sandbox | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 | Through Google's API, or a private endpoint in your own VPC; no public URL documented |
| Outbound internet | Open internet on every plan; no provider-side allowlist | Off unless the template turns it on; can route through your VPC with Cloud NAT, a static IP, Cloud NGFW or Secure Web Proxy |
| Coding agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | Managed Agents API (Preview) runs Google's Antigravity harness; no other coding harness named |
| Keeping keys out of the sandbox | AI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out | You provision and scope the credentials the agent uses |
| Hosting your agent code | You run your own agent loop inside a sandbox | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed |
| Machine size | Up to 8 vCPU / 16 GB on the $20 plan, 16 vCPU / 32 GB from the $100 plan | Runtime: 1, 2, 4, 6 or 8 vCPU and up to 32 GiB; sandbox maximum not published; changing a sandbox means deleting it |
| Regions | EU only: Germany, Finland, France | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | SOC 2 |
Every feature Battleships tracks (43)
| Feature | boat | Google Agent Runtime |
|---|---|---|
| Full VM (own kernel) | Yes | No |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | No |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | Yes |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | Yes |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | No |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No | No |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | Yes |
| Agent harness API | Yes | Yes |
| MCP server | No | No |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | Yes |
| Self-hosting | No | No |
| BYOC | No | No |
| Open source | No | No |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | Yes |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement for Google Agent Runtime or its sandboxes. In StarSling's public run of 2026-09-29, boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB; Google's sandboxes were not part of that run.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Google Agent Runtime 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 | boat, a month | Google Agent Runtime, 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 | $73 · Pay as you go |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $301 · Pay as you go |
| 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 | $3,626 · 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 | $1,030 · Pay as you go |
| 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 | $2,060 · Pay as you go |
boat: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour for what you allocate, rounded to the second, with the first 50 vCPU-hours and 100 GiB-hours free each month. Runtime skips idle time between turns, but sandboxes are billed while they exist; a paused one costs less at a rate Google does not publish, and disk and egress rates are not published either.
Limits in those scenarios
On Google, a sandbox is deleted when its TTL ends, 7 days at most for a custom container, so an agent that never stops needs to be recreated. The 50-agent fleet does not fit because Google's sandboxes have no Docker inside, and every Google row leaves disk and egress unpriced because those rates are not published. On boat the 1,000-job burst is the problem: starts are capped at 90 a minute and 2,400 a day on the $2,000 plan, so the jobs get queued.
| Scenario | boat | Google Agent Runtime |
|---|---|---|
| One coding agent, workdays | 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 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 runs in a locked sandbox.
- A managed home for your agent code. Useful if you build agents with ADK or LangGraph: Agent Runtime hosts them and skips billing for idle time between turns.
- Inside your Google Cloud network. Useful if your agents must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
- Memory snapshots and regions worldwide. Useful if you need to branch a sandbox with its memory, or run in the US or Asia: Google offers both in 23 locations.
Use boat when
your agents need a real computer: root, Docker, SSH, a desktop and public URLs on a full VM that keeps its disk, with Claude Code, Codex and other coding agents built in.
- Root, Docker and a real kernel. Coding agents reach for sudo apt install and docker compose all the time. On Google you would bake every tool into an image ahead of time, and anything that needs Docker has to run somewhere else.
- Public URLs for what agents build. When an agent builds a web app, someone has to open it. On Google you would set up a VPC endpoint, a load balancer or a tunnel yourself to show a preview to a person outside your project.
- Coding agents you drive from outside. If your team uses Claude Code or Codex, Google gives you no built-in way to run them: you install them in an image and pass keys in, where code in the sandbox can read them.
Questions people ask
Is boat cheaper than Google Agent Runtime?
In all five scenarios we priced, yes: one coding agent on workdays comes to $20 a month on boat and $73 on Google, and one agent running all month comes to $26 versus $301. 50 agents in parallel come to $317 versus $3,626, though Google cannot run that fleet without Docker, and sandboxes for your users $200 versus $1,030. For 1,000 short jobs at once, boat comes to $2,000 and Google to $2,060, but boat's start limits queue the jobs. Google's numbers assume a sandbox that exists all those hours; a Runtime agent that sits idle between turns bills less.
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. The sandboxes for code, shell and browser use are a separate part of the same platform called Agent Sandbox.
Can I run Docker or sudo in a Google Agent Sandbox?
No. Shell commands run as the unprivileged user appuser with no sudo, and custom images must not need root, so Docker and nested virtualization are not available. On boat every sandbox is a VM with root, Docker and /dev/kvm.
Can a Google sandbox serve a web app to the public?
Google's docs describe reaching a sandbox through its API or through a private endpoint in your own VPC, not a public URL. On boat a sandbox can serve HTTPS on up to 50 ports, accept raw TCP and get its own IP address.
Where does my data run?
boat runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. Google runs Agent Runtime and sandboxes in 23 locations across the US, Europe, Asia, Canada, Australia and Brazil, inside your own Google Cloud project.
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
- boat vs Oracle Cloud
- boat vs IONOS Cloud
- boat vs AWS AgentCore
- boat vs Contabo
- boat vs Azure Virtual Machines
- boat vs AWS Fargate
- boat vs netcup
- boat vs AWS EC2
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- E2B vs Google Agent Runtime
- Daytona vs Google Agent Runtime
- Modal vs Google Agent Runtime
- Vercel Sandbox vs Google Agent Runtime
- Cloudflare Sandbox vs Google Agent Runtime
- Blaxel vs Google Agent Runtime
- Runloop vs Google Agent Runtime
- Tensorlake vs Google Agent Runtime