boat vs KakaoCloud

KakaoCloud Virtual Machine is a general cloud server in Seoul that you set up yourself. boat is a VM made for AI agents, with coding agents, a 60fps desktop and per-port HTTPS URLs ready. boat costs less in three of the five scenarios below, and KakaoCloud costs less for sandboxes for your users.

Where boat stands out

Coding agents you drive from outside

boat installs Claude Code, Codex, OpenCode and other agents in each sandbox. You drive them from outside with a prompt, steer and events API. A KakaoCloud VM boots a plain OS image, so you install each agent, run it as a process and build the control layer yourself.

A desktop and browser for computer use

Every boat sandbox can stream a 60fps desktop with Chrome, and agents click, type and take screenshots through computer-use tools. You can embed the stream in your own app. On KakaoCloud you set it up: install a desktop, a VNC server and a browser on a Linux VM, or use RDP on a Windows Server image.

A sandbox lifecycle built in

boat saves the disk every minute and at each stop, and you can fork a running sandbox in one call. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Each port can get a token-gated HTTPS URL. On KakaoCloud you set up snapshot schedules, images, public IPs and TLS yourself.

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.

KakaoCloud

KakaoCloud is the public cloud of Kakao Enterprise, a South Korean company. Its Virtual Machine service rents general cloud servers, not agent sandboxes.

You pick an instance type (compute, general, memory, burstable or GPU), boot it from an Ubuntu, Rocky, Alma, CentOS Stream or Windows Server image, and connect over SSH or RDP. Networking, firewalls, disks and images are separate building blocks that you put together in the console or through the OpenAPI. It is made for companies that run general workloads in Korea, including public institutions.

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. “5th cheapest of 365” means 4 of the other 364 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 workloadboat: price rankKakaoCloud: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Both run full VMs. On KakaoCloud you set up the agents, a desktop and preview URLs yourself: install them on the VM, attach a public IP and open ports. boat ships them in every sandbox.
5th cheapest of 365
$634 a month
218th of 365, with limits
$2,326 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
A KakaoCloud VM runs all month with no session cap. You set up the agent service, scheduled volume snapshots and key handling yourself. On boat, turn auto-stop off (default 1 hour) on a paid plan.
6th cheapest of 361
$657 a month
221st of 361, with limits
$1,279 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
KakaoCloud costs less here: $56 against $2,000 a month in our default estimate, with per-minute billing on small burstable instances. boat's start limits make this case expensive on boat.
189th of 336, with limits
$2,000 a month
68th of 336, with limits
$56 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
boat gives each user a sandbox with a token-gated HTTPS URL and no compute charge while stopped. On KakaoCloud you set up public IPs, security groups and TLS for every user yourself.
3rd cheapest of 349
$209 a month
60th of 349, with limits
$427 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Both are a compromise for large rollouts. KakaoCloud's cheapest small instances guarantee only part of each vCPU. boat's start limits make big bursts cost more.
39th of 349, with limits
$2,000 a month
58th of 349, with limits
$3,080 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
10th cheapest of 359
$200 a month
43rd cheapest of 359
$617 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
2nd cheapest of 374
$86 a month
31st cheapest of 374
$312 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
19th cheapest of 371
$26 a month
73rd cheapest of 371
$94 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
boat streams a 60fps desktop with Chrome and computer-use tools. On KakaoCloud you set it up: install a desktop and a VNC server on a Linux VM, or use RDP on a Windows Server image.
7th cheapest of 367
$200 a month
229th of 367, with limits
$634 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
7th cheapest of 356
$200 a month
257th of 356, with limits
$187 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
6th cheapest of 343
$90 a month
257th of 343, with limits
$115 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
73rd of 327, with limits
$1,800 a month
81st of 327, with limits
$2,016 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
KakaoCloud costs less in our default estimate ($93 against $200 a month). boat has fork and per-minute snapshots built in. On KakaoCloud you clone VMs from root-volume images yourself.
3rd cheapest of 351
$200 a month
185th of 351, with limits
$93 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not 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
Not ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureboatKakaoCloud
Kind of productSandbox VMs made for AI agents, created by API in secondsGeneral cloud servers you configure yourself
IsolationEvery sandbox is a full VM with its own kernelEvery instance is a full VM with its own OS
Docker and nested virtualizationDocker, root, systemd and /dev/kvm on every sandboxRoot on the VM, so you can install Docker; KakaoCloud documents that nested virtualization is not supported
Coding agentsSeven harnesses installed (Claude Code, Codex, OpenCode and others), with a prompt, steer and events APIYou set it up: install the agent CLIs on the VM and build your own control layer
Desktop and computer use1920x1080 60fps desktop and Chrome, computer-use tools, embeddable streamYou set it up: install a desktop and VNC on a Linux VM, or connect over RDP to a Windows Server image
Snapshots and stopsDisk saved every minute and at each stop (memory not saved); a stopped sandbox has no compute charge and keeps its disk for at least 14 daysFull or incremental volume snapshots, on demand or on schedules with retention; restore to a new volume. A stopped VM keeps its disk while you pay for it
ForkFork a running sandbox in one call, from its last 1-minute snapshotMake an image of the root volume (running or stopped), then boot new instances from it
Reaching the sandboxUp to 50 token-gated HTTPS URLs; SSH; public IPv6 and outbound IPv4; no dedicated IPv4, and the IP changes at each resumeAttach a fixed public IPv4 and open ports in security groups; you set up TLS yourself
Outbound rulesOpen internet on every plan; no provider-side allowlistSecurity groups with outbound rules by protocol, port and IP range (no domain rules)
Keeping keys out of the sandboxOptional AI credentials proxy ($1 per day on plus $1 per 1,000 requests); with it on, real keys of supported providers stay outside the sandboxSecrets Manager stores secrets that your workloads read; to keep keys off the VM you set up your own proxy
ScaleSet by plan: 100 sandboxes at once and 12 / 60 / 200 included starts per minute / hour / day on $20, up to 2,000 at once on $2,000; extra starts cost $0.03 to $0.07Default project quota of 500 instances and 4,000 vCPU, raised through the Helpdesk
GPUsNone; graphics run on the CPUNVIDIA T4 and A100 instances, plus FuriosaAI NPUs
WindowsNo Windows VM; Windows programs run through Wine on the Linux desktopWindows Server 2019 and 2022 images, billed per instance-hour on top
RegionsGermany, Finland and France; you cannot pick a region; no US or Asia regionSeoul (kr-central-2), plus separate regions for Korean public institutions (kr-gov-central)
ComplianceSOC 2 in progress, no SOC 2 report todayISMS-P, CSAP, ISO/IEC 27001, 27017, 27018, 27701, 27799 and CSA STAR Gold
Compliance and transparencySOC 2 is in progress. We're open about where we stand: live status and data retention policy.No SOC 2 report published
Every feature Battleships tracks (43)
FeatureboatKakaoCloud
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesNo documented way
RootYesYes
SystemdYesNot published
Desktop GUIYesNo documented way
BrowserYesNo documented way
Computer-use APIYesNo documented way
SSHYesYes
Persistent diskYesYes
Pause/resumeYesYes
Automatic snapshotsYesNo documented way
Fork/cloneYesYes
Live fork (no pause)YesYes
Memory forkNo documented wayNo documented way
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNo documented wayNo documented way
Wake on requestNo documented wayNo documented way
HTTPS preview URLsYesYes
Raw TCP inboundYesNot published
Public IPv4No documented wayYes
Egress allowlistNo documented wayYes
Secret proxyYesNo documented way
Secret proxy for any APIYesNo documented way
Preinstalled agentsYesNo documented way
Agent harness APIYesNo documented way
MCP serverNo documented wayNo documented way
GPUNo documented wayYes
WindowsNo documented wayYes
Arm64No documented wayNo documented way
Self-hostingNo documented wayNo documented way
BYOCNo documented wayNo documented way
Open sourceNo documented wayNo documented way
Scoped API keysYesNot published
Spend limitsYesNot published
Usage per sandbox (API)YesNo documented way
Audit logsNo documented wayNot published
SSONo documented wayNo documented way
SOC 2No documented wayNo documented way
HIPAANo documented wayNo documented way
EU data residencyNo documented wayNo documented way
Zero data retentionYesNot published

Performance

boat28.06 runs/s
KakaoCloudNot measured

KakaoCloud is not 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. KakaoCloud's c2a compute instances give full vCPUs. Its t1i burstable instances guarantee only a share of each vCPU, from 5% to 40% by size.

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. KakaoCloud is 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.

Scenarioboat, a monthKakaoCloud, 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$26 · Pay as you go
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$94 · 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$1,153 · Pay as you go
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$187 · 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
$8,800 · $2000/mo · with limits$339 · Pay as you go · with limits

boat: Plans cost $20, $100, $500 or $2,000 a month. The whole plan price comes back as VM time for that month, and unused included time does not carry over. A default 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs. A stopped sandbox has no compute charge, but saved snapshots above the included count and the AI credentials proxy still charge. Above the included starts, each extra start costs $0.03 to $0.07. A card is required, also for the 7-day free trial.

KakaoCloud: KakaoCloud bills each instance per minute at an hourly rate in KRW, before VAT, with no plan fee. Disks, public IPs, outbound traffic and Windows images are billed on top, and a public IP you keep is billed even when unused. New sign-ups can apply within 3 months for KRW 300,000 of credit, granted on approval.

Limits in those scenarios

KakaoCloud has no session cap and no plan fee, so it fits every scenario except the 1,000 short jobs. Its low price for sandboxes for your users comes from t1i burstable instances, which guarantee only a share of each vCPU (20% on t1i.medium, 40% on the largest sizes), so heavy, steady CPU work slows down. A project starts with a quota of 500 instances, so 1,000 jobs at once need a Helpdesk request. boat does not fit the 1,000 short jobs as priced either: even the $2,000 plan includes 2,400 starts a day and 90 a minute, extra starts are paid, and starts above 270 a minute fail with 429. boat never queues a start. On boat, auto-stop defaults to 1 hour, and a stopped sandbox keeps its disk for at least 14 days unless you save a snapshot.

ScenarioboatKakaoCloud
One coding agent, workdaysNone for this scenarioNone for this scenario
One agent that never stopsNone for this scenarioNone for this scenario
50 agents in parallelNone for this scenarioNone for this scenario
Sandboxes for your usersNone for this scenarioNone for this scenario
1,000 short jobs at once
  • 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
  • burstable CPU: 40% of each vCPU guaranteed, throttled above that
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

Which one should you use?

Use KakaoCloud when

you need GPUs, Windows Server, a fixed public IPv4, Korean certifications, or data that stays in South Korea.

  • GPUs and NPUs. Useful if your agents train or test models: KakaoCloud rents NVIDIA T4 and A100 instances, and FuriosaAI NPUs.
  • Windows Server. Useful if you need Windows Server: KakaoCloud boots Windows Server 2019 and 2022 images that you reach over RDP.
  • Data in South Korea. Useful if your users or data must stay in South Korea: KakaoCloud runs in Seoul, with separate regions for public institutions.
  • A fixed public IPv4 and network rules. Useful if a partner allowlists your IP: a KakaoCloud public IPv4 stays the same until you release it.

Use boat when

you run AI agents that need a ready sandbox: coding agents, a desktop, HTTPS URLs, per-minute snapshots and fork, without building that layer on top of plain VMs.

  • Coding agents you drive from outside. On a plain VM you write and maintain the code that starts, prompts and watches every agent, and real AI keys sit on the disk. With boat's optional paid credentials proxy on, the real keys of supported providers stay outside the sandbox.
  • A desktop and browser for computer use. On KakaoCloud each computer-use agent needs that desktop setup, plus your own screen and input layer that you keep working.
  • A sandbox lifecycle built in. Cloning a KakaoCloud VM means making an image of its root volume, then booting a new instance from it. A kept public IP keeps billing even when unused.

Questions people ask

Is boat cheaper than KakaoCloud?

In three of the five scenarios we priced, yes. One coding agent on workdays costs $20 a month on boat and $26 on KakaoCloud. One agent running all month costs $26 against $94. 50 agents in parallel cost $317 against $1,153. For sandboxes for your users, KakaoCloud costs less: $187 on t1i burstable instances against $200 on boat. For 1,000 short jobs at once, neither fits as priced. KakaoCloud prices exclude VAT.

Is KakaoCloud a sandbox for AI agents?

KakaoCloud Virtual Machine is a general cloud server. You can run agents on it: you set up the agent CLIs, a desktop, HTTPS and snapshots yourself. boat is made for agents, with coding agents, a desktop, HTTPS URLs and snapshots ready in every sandbox.

Can I run Docker on KakaoCloud and boat?

Yes on both. A KakaoCloud VM gives you root, so you can install Docker yourself. KakaoCloud documents that nested virtualization is not supported. On boat, Docker, systemd, root and /dev/kvm are ready in every sandbox.

Where does my data run?

KakaoCloud's general region is kr-central-2 in Seoul, South Korea. boat sandboxes run on machines in Germany, Finland and France, and you cannot pick a region. boat can store snapshot copies outside the EU.

Does boat have GPUs or Windows like KakaoCloud?

No. boat has no GPU on any size and no Windows VM. Windows programs run through Wine on its Linux desktop. KakaoCloud has T4 and A100 GPU instances and Windows Server images.

Is boat SOC 2 compliant?

SOC 2 is in progress, and boat has no SOC 2 report today. Live status is at status.ascii.dev and the data retention policy is at docs.boat.dev/data-retention. KakaoCloud lists ISMS-P, CSAP, several ISO/IEC 27000 certificates and CSA STAR Gold.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial

More comparisons