boat vs NAVER Cloud
NAVER Cloud Server is a general cloud VM in Asia that you set up yourself. boat is a VM made for AI agents, with coding agents, a 60fps desktop, per-port HTTPS URLs and snapshots every minute ready. At list prices, boat costs less in the five scenarios below. NAVER Cloud has GPUs, Windows servers and regions in Asia, and boat has none of these.
Where boat stands out
Coding agents you drive from outside
boat installs seven coding-agent harnesses in each sandbox, including Claude Code, Codex and OpenCode, and you drive them from outside with a prompt, steer and events API. A NAVER Cloud server boots a general OS image. You set it up: install each agent, run it as a process and build the control layer.
A desktop and browser for computer use
Every boat sandbox can stream a 60fps desktop with Chrome, and agents can click, type and take screenshots with computer-use tools. You can embed the stream in your own app. On NAVER Cloud you set it up: install a desktop, a VNC server and a browser on Linux, or use RDP on a Windows server.
A sandbox lifecycle built in
boat saves the disk every minute and at each stop. A stopped sandbox costs no machine time and keeps its disk for at least 14 days; saved snapshots still bill. You can fork a running sandbox in one call from its last 1-minute snapshot. Each port can get an HTTPS URL with a token. On NAVER Cloud you set it up: take snapshots or server images, attach public IPs and configure TLS.
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
NAVER Cloud
NAVER Cloud is the public cloud of the NAVER group in South Korea; its Server product rents general cloud VMs, not agent sandboxes.
You pick a server type (Standard, High CPU, High Memory, GPU and more), boot it from a Linux or Windows server image, and connect over SSH or RDP. Networking, ACG firewalls, block storage, public IPs and images are separate building blocks you put together in the console or through the API. It is built for companies running general workloads in Korea and the rest of Asia.
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 workload | boat: price rank | NAVER Cloud: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both run full VMs. On NAVER Cloud you set up the agents, a desktop and preview URLs yourself; boat ships them in every sandbox. | 5th cheapest of 365 $634 a month | 228th of 365, with limits $2,488 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both can run an agent all month. On NAVER Cloud you set up the agent API and key handling yourself, and take snapshots on demand. On boat you turn off auto-stop (default 1 hour), and boat saves the disk every minute. | 6th cheapest of 361 $657 a month | 256th of 361, with limits $2,473 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Both are a compromise for one-minute runs: NAVER Cloud bills by the hour, and boat's start limits (12 a minute on the $20 plan) make big bursts pay for extra starts. | 189th of 336, with limits $2,000 a month | 197th of 336, with limits $4,946 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month 300 servers at once may be above an account's default NAVER Cloud quota, and its public docs do not state that default. A larger quota can need a business account and a review of several days. boat runs 300 at once on the $100 plan. | 3rd cheapest of 349 $209 a month | 155th of 349, with limits $2,033 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 39th of 349, with limits $2,000 a month | 209th of 349, with limits $49,458 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 | 196th of 359, with limits $2,121 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 | 345th of 374, with limits $1,697 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both fit a dev box that runs all month. A NAVER Cloud server has no run cap and can stay stopped up to 90 days at a time. On boat you turn off auto-stop (default 1 hour), and boat keeps a stopped disk for at least 14 days. | 19th cheapest of 371 $26 a month | 80th cheapest of 371 $103 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 NAVER Cloud you set it up: install a desktop, a VNC server and a browser on Linux, or use RDP on a Windows server. | 7th cheapest of 367 $200 a month | 332nd of 367, with limits $2,828 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 | 341st of 356, with limits $2,033 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 | 305th of 343, with limits $407 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 | 209th of 327, with limits $8,130 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month boat forks a sandbox in one call from its last 1-minute snapshot. On NAVER Cloud you set it up: make a server image, then create servers from it. | 3rd cheapest of 351 $200 a month | 267th of 351, with limits $339 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not 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 requirement | Not ranked: misses a requirement |
Key features
| Feature | boat | NAVER Cloud |
|---|---|---|
| Kind of product | Sandbox VMs made for AI agents, created by API | General cloud servers you configure yourself |
| Isolation | Every sandbox is a full VM with its own kernel, on hosts dedicated to boat; vCPUs are shared | Every server is a full VM (KVM on g3, Xen on g1 and g2) |
| Docker and nested virtualization | Docker, root, systemd and /dev/kvm on every sandbox | You get the whole VM, so you can install Docker yourself; the docs do not state nested virtualization |
| Coding agents | Seven harnesses installed, including Claude Code, Codex and OpenCode, with a prompt, steer and events API | You set it up: install each agent on the server and build your own control layer |
| Desktop and computer use | 60fps desktop with Chrome, computer-use tools and an embeddable stream | You set it up: install a desktop and VNC on Linux, or connect over RDP to a Windows server |
| Snapshots and stops | Disk saved every minute and at each stop; a stopped sandbox costs no machine time and keeps its disk for at least 14 days; saved snapshots still bill | Server images and block storage snapshots on demand; a stopped server bills its OS disk and can stay stopped up to 90 days at a time |
| Fork | Fork a running sandbox in one call, from its last 1-minute snapshot | Replica servers from a running source reuse its image and settings but not its data; or boot from a saved server image |
| Reaching the sandbox | HTTPS URLs for up to 50 ports, token-protected; raw TCP on the sandbox IP (IPv4 or IPv6), which changes at each resume | Attach a public IP (billed separately) and open ports in an ACG; you set up TLS yourself |
| Outbound rules | Open internet on every plan; no provider-side allowlist | ACG outbound rules by protocol, port and IP range, up to 50 rules per group (no domain rules) |
| Keeping keys out of the sandbox | Optional AI credentials proxy ($1 a day while on, plus $1 per 1,000 requests): real keys of supported providers and custom HTTPS APIs stay outside the sandbox | Secret Manager stores secrets that your app reads; to keep keys outside the server, you set up your own proxy |
| GPUs | No GPU on any size; graphics run on the CPU | NVIDIA A100, H100, L4 and L40S GPU servers |
| Windows | No Windows VM; Windows programs run through Wine on the Linux desktop | Windows server images, with a Windows tool kit |
| Regions | Germany, Finland and France; no US or Asia region, and you cannot pick one | Korea, Singapore and Japan for g3; older servers also in the U.S. and Germany |
| 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 | NAVER Cloud |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | Not published |
| Root | Yes | Not published |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No documented way |
| Browser | Yes | No documented way |
| Computer-use API | Yes | No documented way |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | No documented way |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | No documented way |
| Memory fork | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No documented way | No documented way |
| Wake on request | No documented way | No documented way |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No documented way | Yes |
| Egress allowlist | No documented way | Yes |
| Secret proxy | Yes | No documented way |
| Secret proxy for any API | Yes | No documented way |
| Preinstalled agents | Yes | No documented way |
| Agent harness API | Yes | No documented way |
| MCP server | No documented way | No documented way |
| GPU | No documented way | Yes |
| Windows | No documented way | Yes |
| Arm64 | No documented way | No documented way |
| Self-hosting | No documented way | No documented way |
| BYOC | No documented way | No documented way |
| Open source | No documented way | No documented way |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | Not published |
| Audit logs | No documented way | Not published |
| SSO | No documented way | Yes |
| SOC 2 | No documented way | Yes |
| HIPAA | No documented way | No documented way |
| EU data residency | No documented way | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement: NAVER Cloud 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), at 4 vCPU / 8 GB, boat did 28.06 runs/s on the V8 Web Tooling Benchmark, second of 15. Every boat sandbox in that run ran on an AMD Ryzen 9 9950X host. The boat fleet also has Ryzen 7 9700X hosts, and boat does not promise a CPU model. NAVER Cloud publishes network, throughput and IOPS levels for each g3 size, but no CPU score we can compare.
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. NAVER Cloud 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.
| Scenario | boat, a month | NAVER Cloud, 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 | $25 · Pay as you go |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $103 · 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 | $1,244 · 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 | $2,033 · Pay as you go · with limits |
| 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 | $13,550 · 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 time does not carry over. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second while it runs. 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 credentials proxy still bill. A card is required, also for the 7-day trial.
NAVER Cloud: NAVER Cloud bills each server pay as you go at a KRW rate before VAT, with no plan fee. We priced its High CPU g3 servers at the same vCPU and memory as each boat size (2 vCPU / 4 GB or 4 vCPU / 8 GB), at Korea prices converted to dollars. Public IPs, extra storage and outbound traffic bill on top, and a stopped server still bills its OS disk.
Limits in those scenarios
NAVER Cloud has no run cap, so one agent on workdays, one agent all month and 50 agents in parallel fit. A stopped NAVER Cloud server can stay stopped up to 90 days at a time and 180 days a year. Its public docs do not state the default server limit (each account sees it in the console), so 300 servers for your users and 1,000 short jobs at once are not confirmed. Requests above the instant limit need a business account and a review that can take several days. On boat, auto-stop defaults to 1 hour; you can turn it off on a paid plan. The $100 plan runs 300 sandboxes at once. The 1,000-job burst passes the included starts even on the $2,000 plan (90 a minute, 600 an hour, 2,400 a day). Extra starts cost $0.03 to $0.07 each, starts above 270 a minute fail with 429, and boat never queues a start.
| Scenario | boat | NAVER Cloud |
|---|---|---|
| One coding agent, workdays | None for this scenario |
|
| One agent that never stops | None for this scenario |
|
| 50 agents in parallel | None for this scenario |
|
| Sandboxes for your users | None for this scenario |
|
| 1,000 short jobs at once |
|
|
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 NAVER Cloud when
you need GPU servers or Windows, or your data must stay in Korea, Japan or Singapore.
- GPU servers. Useful if your agents train or serve models: NAVER Cloud rents NVIDIA A100, H100, L4 and L40S GPU servers.
- Windows servers. Useful if you need Windows: NAVER Cloud boots Windows server images you reach over RDP.
- Data in Korea, Japan and Singapore. Useful if your users or data must stay in Korea, Japan or Singapore, with IP-level outbound firewall rules.
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 general VMs.
- Coding agents you drive from outside. On a general VM you write and maintain the code that starts, prompts and watches every agent. NAVER Cloud's Secret Manager stores keys, and your app reads them. boat's optional paid proxy keeps the real keys of supported providers outside the sandbox.
- A desktop and browser for computer use. On a general VM you also build and maintain the screen and input layer that your agents use.
- A sandbox lifecycle built in. A NAVER Cloud replica server copies the image and settings but not the data, so you make a server image first. boat's limits: memory and running programs are not saved, and the IP changes at each resume.
Questions people ask
Is boat cheaper than NAVER Cloud?
At list prices, in the five scenarios we priced, yes. One coding agent on workdays: $20 a month on boat ($20 is its smallest plan) and $25 on NAVER Cloud. One agent all month: $26 and $103. 50 agents in parallel: $317 and $1,244. 300 sandboxes for your users: $200 and $2,033, and NAVER Cloud's quota for 300 is not confirmed. 1,000 short jobs at once: $8,800 and $13,550, and neither fits that burst as priced. NAVER Cloud prices are before VAT, at the same vCPU and memory as each boat size. The $20 boat plan includes 200 starts a day (12 a minute); extra starts cost $0.03 to $0.07 each. NAVER Cloud has no start limit.
Is NAVER Cloud a sandbox for AI agents?
No. NAVER Cloud Server is a general cloud server: you get a VM with an OS image and set up the agent layer yourself. boat is made for agents, with coding agents, a desktop, HTTPS URLs and snapshots built into every sandbox.
Can I run Docker on NAVER Cloud and boat?
Yes on both. A NAVER Cloud server is a full VM, so you can install Docker yourself; its docs do not state nested virtualization. On boat, Docker, systemd, root and /dev/kvm are ready in every sandbox.
Where does my data run?
NAVER Cloud's current g3 servers run in Korea, Singapore and Japan, and its older server lines also run in the U.S. and Germany. 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 NAVER Cloud?
No. boat has no GPU on any size and no Windows VM; Windows programs run through Wine on its Linux desktop. NAVER Cloud has A100, H100, L4 and L40S GPU servers and Windows server images.
Is boat SOC 2 compliant?
Not yet: boat has no SOC 2 report today, and SOC 2 is in progress. No HIPAA BAA and no SAML SSO are documented. boat measures 99.95% sandbox uptime over the history of all sandboxes, and publishes no SLA. Live status is at status.ascii.dev. NAVER Cloud lists SOC 1, 2 and 3, several ISO/IEC certificates, CSA STAR, PCI DSS, ISMS-P and CSAP.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial