boat vs CloudCruise
CloudCruise builds and runs browser workflows for healthcare portals and EHRs, with agents that write and repair them. boat gives your agent a whole Linux machine with Chromium inside, where it can also run code, Docker and servers, keep its files and work for as long as it needs.
Where boat stands out
A whole machine around the browser
A boat sandbox is a full Linux VM with root, a shell, Docker, systemd and /dev/kvm, with Chromium and a 60fps desktop already inside. Your agent can browse a portal, save what it found, process it with any tool, and serve the result, all on one machine.
Keeps its files and runs as long as it needs
boat has no session cap on paid plans. The whole disk is saved every minute and when the sandbox stops, a stopped sandbox costs nothing, and you can fork a running one to try several paths at once.
Your own coding agents, with keys kept outside
Claude Code, Codex and other coding agents come preinstalled, and you prompt, steer and follow them through one API. A credentials proxy keeps real API keys outside the sandbox for any HTTPS API, and switches 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
CloudCruise
CloudCruise is a platform for building and running browser automations, now focused on healthcare work such as payer portals, EHRs, revenue cycle and credentialing.
CloudCruise is a different kind of product from boat. A Builder Agent turns a plain-English prompt into a deterministic workflow graph, CloudCruise runs it on its own machines through a Run API, and a Maintenance Agent sorts failures, recovers broken selectors and retries. You never get a shell on the machine; it is built for teams that need reliable automations against sites with no API.
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 | CloudCruise: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs a shell, Docker and a place to build and test, and a CloudCruise run only executes a browser workflow. | 3rd cheapest of 367 $634 a month | 365th of 367, with limits $52,794 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month needs a disk that stays, and CloudCruise keeps only saved logins and cookies between runs. | 5th cheapest of 366 $657 a month | 365th of 366, with limits $109 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 186th of 345, with limits $2,000 a month | 338th of 345, with limits $9,994 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Sandboxes for your users need a general machine per user, and CloudCruise runs workflows you built on its platform. | Cheapest of 361 $209 a month | 351st of 361, with limits $34,869 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 | 337th of 360, with limits $150 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 | 341st of 364, with limits $14,994 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI runners need Docker, root and a disk for build caches, which CloudCruise's browser machines do not offer. | 4th cheapest of 377 $86 a month | 361st of 377, with limits $3,594 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 18th cheapest of 368 $26 a month | 366th of 368, with limits $2,184 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month boat streams a full Linux desktop at 60fps that your own agent drives, while CloudCruise uses screenshot clicks only inside its own workflows. | 6th cheapest of 369 $200 a month | 366th of 369, with limits $14,994 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit; CloudCruise turns a browser task into a workflow it runs and repairs for you, while boat gives the agent a shell, files and a desktop next to Chromium. | 7th cheapest of 367 $200 a month | 47th cheapest of 367 $14,994 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month Both fit startup-scale bots; CloudCruise includes proxies and retries, while boat gives each bot a whole machine whose disk keeps its files. | 6th cheapest of 346 $90 a month | 85th cheapest of 346 $14,994 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Sites with strong bot checks need stealth fingerprints, CAPTCHA steps and proxies, which CloudCruise includes and boat does not. | 71st of 338, with limits $1,800 a month | 30th of 338, with limits $300 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 | 96th of 360, with limits $7,494 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 | CloudCruise |
|---|---|---|
| What you get | A full Linux VM with its own kernel and root, on dedicated AMD Ryzen 9 9950X hosts | A managed VM that runs one browser workflow, started through the Run API |
| Shell, code and Docker | SSH, any language, Docker, systemd and nested virtualization (/dev/kvm) | Workflow nodes only (navigate, click, extract, loop, API call); no shell, SSH or Docker |
| Desktop and computer use | A full Linux desktop streamed at 60fps, or Chromium alone; your agent drives it and you can embed it | Browser only, with a live view of the session; screenshot clicks are a mode inside its workflows |
| State between runs | The whole disk is saved every minute and on stop; fork a running sandbox | Each run is fresh; the Vault keeps cookies and local storage for saved logins |
| Machine size | Up to 16 vCPU / 32 GB on the $100 plan and above | Not published or selectable |
| Building automations | Your agent writes its own scripts or browses directly; nothing is built for you | Builder Agent turns a prompt into a deterministic workflow, with versions and rollbacks |
| Repairing failures | Your own code handles retries and errors | Maintenance Agent sorts errors, recovers broken selectors and retries with backoff |
| Stealth and CAPTCHAs | Chromium on datacenter IPs; no fingerprint rotation or CAPTCHA solving | Laptop-like fingerprints, human-like input and a CAPTCHA step |
| Proxies | None managed; you can run your own proxy client inside the VM | Managed pool by random, closest IP or country, off by default; your own proxy on Enterprise |
| Logging in to sites | Your agent logs in itself; boat switches AI credentials to another account when credits run out | Encrypted Vault with TOTP, 2FA by SMS, email or magic link, and 1Password |
| Agents | Claude Code, Codex and other coding agents preinstalled, with a prompt, steer and events API | Its own Builder and Maintenance agents; a CLI lets coding agents on your machine manage workflows |
| Keeping secrets from the agent | Credentials proxy: real keys never enter the sandbox, for any HTTPS API | Site passwords are decrypted in memory inside the worker and typed into login forms |
| Hosting | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP | No ports of your own; you reach runs through the API, webhooks and the live view |
| Data location | EU only (Germany, Finland, France), with zero data retention | Region not published; run videos, screenshots and logs kept 30 days |
| 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 | CloudCruise |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | Not published |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | No |
| SSH | Yes | No |
| Persistent disk | Yes | No |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | No |
| Live fork (no pause) | Yes | No |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Not published |
| ≥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 | No |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | No |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | No |
| 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 | No |
| Audit logs | No | Yes |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | No |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. CloudCruise does not publish its machine size and is not in the CPU benchmark. boat scored 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. CloudCruise 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 | CloudCruise, 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 | $522 · Starter · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $2,184 · Starter · with limits |
| 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 | $26,394 · Starter · 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 | $14,994 · Starter · with limits |
| 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 | $29,994 · Starter · with limits |
boat: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
CloudCruise: CloudCruise bills automation hours: Starter is free with 2 hours, then $3 an hour, and the hour includes the VM, proxies and AI usage. Scale costs $700 a month with volume discounts but no published rate, and Accelerate and Enterprise are custom.
Limits in those scenarios
No scenario on this page fits CloudCruise as written, because each one asks for a general machine with a disk, and CloudCruise runs browser workflows on unsized machines that start fresh each time. It does not publish how many runs can go at once; extra runs wait in its queue, and reserved instances are an Enterprise feature. Its hour also includes AI and proxies, so the totals are not a like-for-like machine price. boat fits every scenario except 1,000 short jobs at once, where even its $2,000 plan queues the starts.
| Scenario | boat | CloudCruise |
|---|---|---|
| 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 CloudCruise when
you want browser workflows on healthcare portals or EHRs built, run, repaired and retried for you, with logins, 2FA, stealth and proxies handled.
- Workflows built and repaired for you. For teams that want working portal automations without writing them: an agent builds the workflow and another one repairs and retries it.
- Made for healthcare portals. For healthcare teams: payer portals, EHRs and Citrix desktops, with logins, 2FA and a BAA on every plan.
- Stealth and proxies included. For sites with bot checks: laptop-like fingerprints, human-like input, a CAPTCHA step and managed proxies in the hourly price.
Use boat when
your agent does more than follow a browser workflow: it needs a shell, Docker, a desktop or a server next to Chromium, runs for hours, and has to keep its work between runs.
- A whole machine around the browser. A CloudCruise run executes workflow nodes and nothing else. An agent that also needs to install tools, run code on the data or use a desktop app has to do that on a second service.
- Keeps its files and runs as long as it needs. Each CloudCruise run starts on a fresh machine and only cookies and local storage carry over, so downloads, installed tools and working files start over every time.
- Your own coding agents, with keys kept outside. CloudCruise's agents build and fix workflows inside its own platform, so you cannot bring your own agent loop. An agent that writes code and calls APIs needs its keys kept where it cannot read them.
Questions people ask
Is CloudCruise a sandbox like boat?
No. CloudCruise builds and runs browser workflows on its own machines, and you control them through its Run API, not a shell. boat gives you a whole Linux VM with Chromium, a desktop, Docker and root, so the browser is one tool among many.
Is boat cheaper than CloudCruise?
In the scenarios on this page, yes: one coding agent on workdays costs $20 on boat against $522, and one agent running all month $26 against $2,184. CloudCruise fits none of them as a general machine, and its $3 hour also pays for AI usage and proxies, which boat does not include.
Can I run browser automations on boat?
Yes. Each boat sandbox has Chromium and a full Linux system, so you can install Playwright or a browser agent and run it on a schedule you set up. You handle retries and logins in your own code, and the disk keeps browser profiles and downloads between runs.
Which one is better at getting past bot checks?
CloudCruise. It gives each run laptop-like fingerprints and human-like input, has a CAPTCHA step, and includes a managed proxy pool. boat runs Chromium on datacenter IPs.
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