boat vs BrowserCloud
BrowserCloud is a browser API: you connect Puppeteer or Playwright to a remote Chrome in a container and pay in browser-hours. boat gives each agent a full Linux VM with Chromium, a 60fps desktop, Docker and a disk that persists, so the same machine can browse, run code and host what it builds.
Where boat stands out
A machine, not only a browser
A boat sandbox is a full VM with root, SSH, systemd, Docker and /dev/kvm, with Chromium already inside it. A BrowserCloud session gives you a Chrome you control over CDP or an HTTP call, and nothing outside that browser. Your agent's code, tools and data have to live on another machine.
A disk that stays, and forks
On boat the whole disk persists, with snapshots every minute and on stop, and you can fork a running sandbox into copies. BrowserCloud starts each session with a fresh profile; a context id carries cookies and storage to the next one, and nothing else survives.
A desktop and coding agents you drive from outside
boat streams a 60fps Linux desktop with Chromium, so a computer-use agent can open any app, and it ships Claude Code, Codex, OpenCode and other agents you prompt, steer and follow through one API. BrowserCloud shows a live view of the Chrome tab, and the agent itself runs on your side.
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
BrowserCloud
BrowserCloud sells browsers as a service: remote Chrome sessions for scraping, testing and AI agents, reached over a WebSocket or an HTTP API.
You point Puppeteer, Playwright or Browser Use at a BrowserCloud WebSocket URL, or call HTTP endpoints for page content, PDFs, screenshots and custom scripts. Each browser runs in an isolated container with stealth fingerprints, datacenter and residential proxies, live view and session recording, and everything is paid from one monthly credit pool. It is a managed browser, not a machine you get a shell on, so this page compares where it overlaps with boat: agents that browse and scrape.
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 | BrowserCloud: 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 disk; BrowserCloud exposes only a browser, so it can serve as a tool for the agent but not as its machine. | 3rd cheapest of 367 $634 a month | 158th of 367, with limits $1,461 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine needs files that stay; BrowserCloud keeps only a browser profile between sessions. | 5th cheapest of 366 $657 a month | 236th of 366, with limits $3,030 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Neither fits code interpreter bursts well: BrowserCloud runs no user code outside the browser, and boat's start limits queue very large bursts. | 186th of 345, with limits $2,000 a month | 255th of 345, with limits $277 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month | Cheapest of 361 $209 a month | 241st of 361, with limits $965 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 | 256th of 360, with limits $4,150 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 | 256th of 364, with limits $415 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 4th cheapest of 377 $86 a month | 236th of 377, with limits $119 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 18th cheapest of 368 $26 a month | 253rd of 368, with limits $99 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month BrowserCloud drives a Chrome tab, not a desktop; boat streams a 60fps Linux desktop where a computer-use agent can open any app. | 6th cheapest of 369 $200 a month | 158th of 369, with limits $415 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit: BrowserCloud gives a stealth Chrome over CDP with proxies, and boat gives Chromium on a full VM where the same agent can also save files and run code. | 7th cheapest of 367 $200 a month | 23rd cheapest of 367 $415 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month Both fit at startup scale; BrowserCloud's HTTP API returns page content, PDFs and screenshots per request, so small jobs may not need a session at all. | 6th cheapest of 346 $90 a month | 42nd cheapest of 346 $415 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month BrowserCloud fits mass scraping better: residential proxies in 195 countries, stealth modes and CAPTCHA solving are part of its plans, while boat uses datacenter IPs and solves no CAPTCHAs. | 71st of 338, with limits $1,800 a month | 10th of 338, with limits $8,300 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 | 221st of 360, with limits $248 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 | BrowserCloud |
|---|---|---|
| Kind of product | A full Linux VM per sandbox, with a desktop and Chromium inside | Managed remote Chrome sessions plus HTTP APIs for content, PDF and screenshots |
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Isolated container per browser, with dedicated CPUs per browser |
| Running your own code | Root, SSH, systemd, Docker and /dev/kvm on every machine | Puppeteer scripts and page JavaScript only; no shell, Docker or SSH |
| Files after a session | The disk persists, with snapshots every minute and on stop; a stopped sandbox costs nothing | A new profile each session by default; a context id keeps cookies and storage, and no other files survive |
| Session length | No cap on paid plans; you set the time to live | Free caps sessions at 15 minutes; paid plans set a timeout, 30 seconds by default, with no published maximum |
| Desktop and computer use | 60fps desktop and Chromium, computer use and browser control, embeddable stream | Live view and recording of the Chrome session; no desktop or computer-use API |
| Bot detection | Datacenter IPs and Chromium; no CAPTCHA solving | Stealth modes and fingerprint randomization on all plans, auto CAPTCHA solving from Hobby, advanced stealth from Startup |
| Proxies | The machine's own datacenter IP; bring your own proxy | Datacenter and residential proxies with rotation, sticky IPs and country targeting; your own proxy from Startup |
| Fork and snapshots | Fork a running sandbox with its disk; named snapshots to start new ones from | No snapshots or fork; only a saved browser profile |
| Hosting what the agent builds | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 | None; the only endpoint is BrowserCloud's own browser host |
| Coding agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | None; your own agent, such as Browser Use, runs elsewhere and connects over CDP |
| 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 | Not applicable: the agent and its keys stay on your side |
| Concurrency | 100 sandboxes at once from the $20 plan, up to 2,000 by plan | 1, 5, 50, 100 browsers by plan, 300+ on Enterprise, or a dedicated cluster of 100 to 400 |
| Where it runs | EU only: Germany, Finland, France, with EU data residency | Data centers in North America, Europe and Asia on DigitalOcean, cities not named; proxies in 195 countries |
| 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 | BrowserCloud |
|---|---|---|
| Full VM (own kernel) | Yes | No |
| 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 | Not published |
| SSO | No | No |
| SOC 2 | No | Yes |
| HIPAA | No | No |
| EU data residency | Yes | No |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. BrowserCloud was not in StarSling's public CPU benchmark and does not publish the CPU or memory behind a browser session, so there is no number to set against boat's 26.69 runs per second at 4 vCPU / 8 GB. BrowserCloud says its browsers start in under 300 ms with dedicated CPUs per browser.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. BrowserCloud 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 | BrowserCloud, 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 | $249 · Business · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $249 · Business · 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 | $730 · Business · 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 | $415 · Business · 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 | $830 · Business · with limits |
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.
BrowserCloud: Each plan is a monthly credit pool: 1,000 credits buy one browser-hour on the pricing page, and the same pool pays for HTTP calls and proxy traffic. Hobby ($19) is 120 browser-hours, Startup ($99) 1,000 and Business ($249) 3,000; unused credits do not carry over, and the overage rate is not published.
Limits in those scenarios
The BrowserCloud prices in the table are for a browser session of unpublished size with no disk that stays, so none of them is a 4 vCPU / 8 GB machine and none of the scenarios fully fits. Concurrency is the next limit: 100 browsers at once on Business, so 300 sandboxes for your users and 1,000 short jobs at once need Enterprise or a dedicated cluster. On boat, the 1,000-job burst is the one that does not fit: bursts above 90 starts a minute are queued, and it needs more starts per day than the top plan allows.
| Scenario | boat | BrowserCloud |
|---|---|---|
| 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 BrowserCloud when
your job is the browser itself: scraping sites that block bots with stealth, residential proxies and CAPTCHA solving, one-shot HTML, PDF or screenshot calls, or hundreds of parallel browsers on a flat-rate cluster.
- Stealth, proxies and CAPTCHA solving. Useful for scraping sites that block bots: stealth fingerprints, residential proxies in 195 countries and CAPTCHA solving come with the paid plans.
- Requests without a session. Useful when you only need a page's HTML, a PDF or a screenshot: one HTTP call does it, priced per request.
- Flat-rate browser clusters. Useful for steady high-volume browser work: dedicated clusters of 100 to 400 parallel sessions at a flat monthly price, with no credit limits.
Use boat when
your agent browses and also works: it keeps files, runs code, Docker and dev servers, uses a full desktop, and hosts what it builds on one VM that runs as long as the task takes.
- A machine, not only a browser. A browser agent that downloads a report, parses it and writes code from it needs somewhere to run all of that. With BrowserCloud you run and pay for that second machine yourself and wire the two together.
- A disk that stays, and forks. Downloads, logs and half-done work vanish when a BrowserCloud session ends. An agent that works over days must ship every file out before the timeout, or start again.
- A desktop and coding agents you drive from outside. Tasks that leave the browser, like a file dialog, a desktop app or a terminal, stall an agent that only has a Chrome tab. On BrowserCloud you build and host the agent loop yourself.
Questions people ask
Is boat cheaper than BrowserCloud?
They sell different things, so the table sets a boat VM against a BrowserCloud browser session that keeps no disk. 50 agents in parallel come to $317 on boat against $730, and sandboxes for your users to $200 against $415. For 1,000 short jobs at once, BrowserCloud's browser-hours come to less, but neither fits that burst without higher limits.
Can I run my own code on BrowserCloud?
Only inside the browser: Puppeteer scripts through its HTTP API and JavaScript on the page. There is no shell, SSH or Docker. On boat every sandbox is a full VM with root, Docker and SSH.
Does BrowserCloud keep my files between sessions?
Each session starts with a fresh browser profile. If you pass a context id, cookies and storage carry over; other files do not. boat keeps the whole disk, with snapshots every minute and on stop.
Does boat have stealth mode or CAPTCHA solving like BrowserCloud?
No. boat runs Chromium on datacenter IPs and does not solve CAPTCHAs. For scraping sites that block bots at volume, BrowserCloud's stealth modes, residential proxies and CAPTCHA solving are built for that.
Can I use boat and BrowserCloud together?
Yes. An agent on a boat sandbox can connect Puppeteer or Playwright to a BrowserCloud WebSocket URL for stealth browsing, and keep its code, files and tools on the boat VM.
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. boat runs only in the EU, with a zero data retention option.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial