Deno Sandbox vs Google Agent Runtime

Deno Sandbox gives code a small Firecracker microVM that Deno says starts in under 200 ms and lives up to 30 minutes; it is closed to new customers since November 2026. Google Agent Runtime hosts your agent code on Google Cloud, and its Agent Sandbox runs code as an unprivileged user in a gVisor-isolated container for up to 7 days.

The companies and products

Deno Sandbox

Deno Sandbox comes from the company behind the Deno runtime and runs untrusted or AI-generated code in Linux microVMs. Since November 2026 it is not part of Deno Deploy plans and is not available to new customers.

Each sandbox is a Firecracker microVM with 2 vCPU, 768 MB to 4 GB of memory and a 10 GB disk that is wiped when it ends, created from a TypeScript or Python SDK. A bootable volume (Chicago only) can be the root disk and keep its files. Deno Deploy can limit outbound traffic to a host allowlist and swap placeholder secrets for real ones. A sandbox can be promoted to a Deno Deploy app.

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. Each sandbox runs in a gVisor-isolated container in a Google-managed tenant project. Teams on GKE can also run the open-source GKE Agent Sandbox in their own cluster, with gVisor or Kata Containers, and manage it themselves.

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. “2nd cheapest of 365” means 1 of the other 364 providers runs 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 workloadDeno Sandbox: price rankGoogle Agent Runtime: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
A software factory needs hours, root and Docker. Deno stops after 30 minutes at 2 vCPU and does not document Docker. Google's sandboxes run without root and document no Docker; you build images outside. boat has root, Docker and /dev/kvm on a full VM.
No published price310th of 365, with limits
$5,801 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
A Google sandbox lives up to 7 days, and a snapshot (Preview) carries its files and memory into a new one. A Deno sandbox ends after 30 minutes. boat has no session cap once auto-stop is off (default 1 hour), but a resume is like a reboot.
No published price34th cheapest of 361
$7,519 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Google's Code Execution sandbox is a ready Python and JavaScript interpreter billed only for use. Deno also suits short runs, but it is closed to new customers since November 2026.
No published price251st of 336, with limits
$275 a month
189th of 336, 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
Deno Sandbox is closed to new customers; existing organizations get 5 at once by default. Google documents no public URL into a sandbox. boat serves HTTPS URLs on up to 50 ports, token-gated by default.
No published price275th of 349, with limits
$1,916 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
No published price132nd of 349, with limits
$8,240 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
No published price90th cheapest of 359
$2,060 a month
10th cheapest of 359
$200 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. Google documents none inside its sandboxes, and Deno does not document it. boat runs Docker and systemd on every VM.
No published price104th cheapest of 374
$989 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
Deno has SSH, and a bootable volume in Chicago keeps files. Google documents no SSH; each execute_bash() call runs in a new shell. boat gives SSH, a desktop and a disk saved every minute.
No published price317th of 371, with limits
$241 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Google runs a browser with a VNC live view, a click and type API and CDP. Deno documents no desktop. boat streams a full Linux desktop at 1920x1080, 60 fps.
No published price85th of 367, with limits
$1,648 a month
7th cheapest of 367
$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. On Deno you install a browser yourself with apt-get, within 4 GB of memory. boat runs Chrome on a desktop you can watch.
No published price132nd of 356, with limits
$824 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
No published price56th cheapest of 343
$515 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
No published price212th of 327, with limits
$8,240 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
No published price281st of 351, with limits
$412 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
No published priceNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
No published priceNot ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureDeno SandboxGoogle Agent Runtimeboat
IsolationFirecracker microVM with its own kernelgVisor-isolated container in a Google-managed tenant projectFull VM with its own kernel, on hosts dedicated to boat (AMD Ryzen 7 9700X or Ryzen 9 9950X); vCPUs are shared
Root and DockerDocker and nested virtualization not documentedRuns as appuser with no sudo; images must not need root; Docker and /dev/kvm not documentedRoot, systemd, Docker and /dev/kvm on every VM
Machine size2 vCPU (no CPU option documented), 768 MB to 4 GB memory, 10 GB diskRuntime: 1 to 8 vCPU and up to 32 GiB; sandbox maximum not published2 to 16 vCPU and 4 to 32 GB, 51 to 251 GB disk; 16 vCPU needs the $100 plan or higher
How long a sandbox livesUp to 30 minutes; longer work can be promoted to a Deno Deploy appTTL of up to 7 days for a custom container, 14 days for Code Execution; a snapshot carries state into a new sandboxAuto-stop defaults to 1 hour; set up to 30 days, or turn it off on a paid plan for no cap
Files after it endsDefault root disk is wiped at the end; a bootable volume (300 MB to 20 GB, Chicago only) can be the root filesystem and keeps its filesPause keeps the file system; a snapshot (Preview) saves files and memory and restores into a new sandboxDisk saved every minute and at each stop, kept at least 14 days after a stop; memory is not saved
Snapshots and branchingOn-demand read-only volume snapshots that many new sandboxes can boot from (Chicago only)Snapshots (Preview) keep memory and files; start many sandboxes from oneFork a running sandbox from its last 1-minute snapshot; resume is like a reboot
Shell accessSSH and a browser VS Code editorexecute_bash() API calls, each in a new shell; SSH not documentedSSH, plus an API for commands
Reaching what it servesPublic HTTPS URL per exposed port, without authenticationGoogle's API or a private endpoint in your VPC; public URL not documentedHTTPS URLs on up to 50 ports, token-gated by default; SSH
Desktop and browserNo desktop documented; you install a browser with apt-getBrowser in a container with a VNC view, click and type API and CDP; a full desktop is not documentedLinux desktop and Chrome streamed at 1920x1080, 60 fps, with computer-use tools
Outbound rulesHost allowlist per sandbox (allowNet), enforced by Deno Deploy outside your codeOff unless the template turns it on; route through your VPC firewallOpen internet, no provider-side allowlist
Keeping API keys outAny secret swapped in on outbound HTTPS requests to approved hosts; the sandbox sees a placeholderYou provision and scope the credentials the agent usesOptional paid proxy ($1 a day while on, plus $1 per 1,000 requests) for supported model providers; other secrets enter the sandbox
Coding agentsRoot image with Claude Code, run through shell commandsManaged Agents API (Preview) runs Google's Antigravity harness; others go in a custom imageSeven agents installed, with a prompt, steer and events API
Hosting agent codeA sandbox can be promoted to a Deno Deploy appDeploys ADK, LangGraph and other agents; idle time between turns not billedYou run your own agent loop inside a sandbox
Availability and regionsNot available to new customers since November 2026; Amsterdam and Chicago23 locations worldwideSelf-serve from $20 a month; Germany, Finland and France, no US or Asia region
Every feature Battleships tracks (43)
FeatureDeno SandboxGoogle Agent Runtimeboat
Full VM (own kernel)YesNo documented wayYes
Docker insideNot publishedNo documented wayYes
Nested virtualizationNo documented wayNo documented wayYes
RootYesNo documented wayYes
SystemdNot publishedNot publishedYes
Desktop GUINo documented wayNot publishedYes
BrowserNo documented wayYesYes
Computer-use APINo documented wayYesYes
SSHYesNo documented wayYes
Persistent diskYesYesYes
Pause/resumeNo documented wayYesYes
Automatic snapshotsNo documented wayYesYes
Fork/cloneNo documented wayYesYes
Live fork (no pause)No documented wayYesYes
Memory forkNo documented wayYesNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsNo documented wayYesYes
Idle auto-stopNo documented wayNo documented wayNo documented way
Wake on requestNo documented wayNo documented wayNo documented way
HTTPS preview URLsYesNo documented wayYes
Raw TCP inboundNo documented wayNot publishedYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistYesYesNo documented way
Secret proxyYesNo documented wayYes
Secret proxy for any APIYesNo documented wayYes
Preinstalled agentsYesYesYes
Agent harness APINo documented wayYesYes
MCP serverNo documented wayNo documented wayNo documented way
GPUNo documented wayNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayYesNo documented way
Self-hostingNo documented wayNo documented wayNo documented way
BYOCNo documented wayNo documented wayNo documented way
Open sourceNo documented wayNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)No documented wayYesYes
Audit logsNot publishedNot publishedNo documented way
SSONo documented wayYesNo documented way
SOC 2Not publishedYesNo documented way
HIPAANot publishedYesNo documented way
EU data residencyYesYesNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

Deno SandboxNot measured
Google Agent RuntimeNot measured
boat28.06 runs/s

Neither Deno Sandbox nor Google Agent Runtime is in the public benchmarks we use, so we cannot say which is faster. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Deno Sandbox and Google Agent Runtime are not in the public benchmarks we use, so we cannot say which is faster.

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. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioDeno Sandbox, a monthGoogle Agent Runtime, a monthboat, 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
No published price$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
No published price$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
No published price$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
No published price$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
No published price$2,060 · Pay as you go$8,800 · $2000/mo · with limits

Deno Sandbox: Deno Sandbox is no longer included in Deno Deploy plans and is not available to new customers (November 2026). Deno publishes no current sandbox rates, so it has no price in our scenarios. The launch post listed $0.05 per hour of CPU time, $0.016 per GB-hour of memory and $0.20 per GiB-month of volume storage.

Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, rounded to the second. The pricing page lists 50 vCPU-hours and 100 GiB-hours free each month but does not say they cover sandboxes. Sandboxes bill while they exist, Runtime skips idle time between turns, and disk, snapshot and egress rates are not published.

Google Agent Runtime: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; saved snapshots above the included count and the AI proxy, if on, still charge. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07.

Limits in those scenarios

Deno Sandbox is closed to new customers, so it has no price in our scenarios; existing organizations get 5 sandboxes at once by default, each living up to 30 minutes on 2 vCPU and up to 4 GB. Google fits four of the five scenarios but leaves disk and egress unpriced, and the 50-agent fleet does not fit because Google documents no Docker in its sandboxes. boat has limits too: auto-stop defaults to 1 hour, and the $2,000 plan includes 90 starts a minute; extra starts cost $0.03 to $0.07, and starts above 270 a minute fail with 429, so boat does not fit 1,000 jobs at once. Google fits that burst at $2,060 a month.

ScenarioDeno SandboxGoogle Agent Runtimeboat
One coding agent, workdays
  • discontinued / closed to new customers
  • disk beyond 0 GiB: price unknown
  • egress price not published
None for this scenario
One agent that never stops
  • discontinued / closed to new customers
  • disk beyond 0 GiB: price unknown
  • egress price not published
None for this scenario
50 agents in parallel
  • discontinued / closed to new customers
  • missing Docker inside
  • disk beyond 0 GiB: price unknown
  • egress price not published
None for this scenario
Sandboxes for your users
  • discontinued / closed to new customers
  • disk beyond 0 GiB: price unknown
  • egress price not published
None for this scenario
1,000 short jobs at once
  • discontinued / closed to new customers
  • disk beyond 0 GiB: price unknown
  • egress price not published
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use Deno Sandbox when

Use Deno Sandbox if your organization already has it and you run short pieces of untrusted code that must start in milliseconds and reach only hosts you allow. New customers cannot sign up since November 2026.

  • Fast starts for short code. Good for short bursts of code: Deno says a sandbox starts in under 200 ms. Only existing organizations can use it since November 2026.
  • A public URL and SSH. Useful for a quick preview: Deno gives SSH and a public HTTPS URL per exposed port.
  • Secrets swapped outside your code. Good for untrusted code: Deno Deploy allows only listed hosts and swaps placeholder secrets for real ones.

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.

  • A managed home for agent code. Useful if you build with ADK or LangGraph: Agent Runtime hosts your agents and skips idle time between turns.
  • Sandboxes that last for days. Fits longer tasks than Deno allows: a sandbox can live up to 7 days and snapshot its memory to branch (Preview).
  • Inside your Google Cloud network. Useful if agents must stay in your Google Cloud perimeter, with egress off by default, in 23 locations.

Where boat fits

Deno Sandbox is built for short runs, and Google Agent Runtime for agents that live inside Google Cloud. If your agents do real work for hours, with installs, Docker, a desktop and something to show people, boat gives each one a full VM whose disk is saved every minute.

Root, Docker and /dev/kvm

Google's sandboxes run without sudo and document no Docker; you bake tools into a custom image and run Docker elsewhere. Deno does not document Docker. boat has root, Docker, systemd and /dev/kvm.

A machine that stays

A Deno sandbox ends after 30 minutes, and only a volume in Chicago keeps files. A Google sandbox ends at its TTL, 7 days at most, and a snapshot carries it on. boat has no cap once auto-stop is off and saves the disk every minute.

Agents, desktop and URLs

Deno documents no desktop, and Google documents only a browser and no public URL. boat installs seven agents you drive from outside, a 60 fps desktop and HTTPS URLs on up to 50 ports.

Use boat when your agents need a full VM for hours or weeks: root, Docker, SSH, a desktop and HTTPS URLs, with the disk saved every minute and seven coding agents installed. Compare it one to one: boat vs Deno Sandbox and boat vs Google Agent Runtime.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is Deno Sandbox cheaper than Google Agent Runtime?

We cannot compare today. Deno Sandbox is closed to new customers since November 2026 and publishes no current rates. In our scenarios Google costs $73 a month for one agent on workdays, and boat $20; for 1,000 short jobs at once Google costs $2,060, and boat's start limits do not fit.

Which is faster?

We cannot say: neither is in the public benchmarks we use. Deno states starts under 200 ms; that is its own figure. In StarSling's run of 3 October 2026, boat did 28.06 runs/s at 4 vCPU / 8 GB, on an AMD Ryzen 9 9950X host.

Can Deno Sandbox or Google Agent Runtime run Docker?

Google's managed sandboxes run commands as appuser with no sudo, and Google documents no Docker inside; you build images outside and push them to Artifact Registry. Deno's docs do not mention Docker or nested virtualization. boat runs Docker and systemd and exposes /dev/kvm on every VM.

How long can a sandbox run on each?

A Deno sandbox lives up to 30 minutes, unless you promote it to a Deno Deploy app. A Google sandbox lives up to 7 days for a custom container or 14 days for Code Execution, and a snapshot (Preview) carries it into a new one. boat has no session cap once auto-stop is off on a paid plan (default 1 hour).

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 serve a web app to the public?

Deno gives each exposed port a public HTTPS URL, without authentication. Google's docs describe only its API or a private endpoint in your VPC. boat serves HTTPS URLs on up to 50 ports, token-gated by default.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons