boat vs Hyperbrowser
Hyperbrowser is a browser company first: cloud Chrome with stealth, proxies and CAPTCHA solving, plus short-lived Firecracker sandboxes for code. boat gives each agent one full Linux VM with Docker, a disk that persists, a 60fps desktop with Chromium and coding agents you drive from outside.
Where boat stands out
One machine that keeps running and keeps its files
A boat sandbox has no session cap on paid plans, and its disk persists with snapshots every minute and on stop, so a stopped sandbox costs nothing and comes back with its files. A Hyperbrowser sandbox lives at most 24 hours from VM start, and when it stops its disk is gone unless you saved work to a volume or took a memory snapshot.
Docker, systemd and /dev/kvm on a full VM
Every boat sandbox is a full VM with root, SSH, systemd, Docker and nested virtualization, on dedicated AMD Ryzen 9 9950X hosts. Hyperbrowser's sandbox docs cover exec, processes and a terminal API, and use Docker only to build images on your own machine. Running containers or emulators inside a Hyperbrowser sandbox is not documented.
Coding agents you drive from outside, keys kept outside
boat ships Claude Code, Codex, OpenCode and other agents in each sandbox, and you prompt, steer and follow them through one API with an event stream. Hyperbrowser's claude-code and codex images install the CLI, and you run it yourself through exec. boat's credentials proxy keeps real API keys outside the sandbox for model providers and any HTTPS API.
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
Hyperbrowser
Hyperbrowser calls itself the AI agents' gateway to the internet: cloud browsers, sandboxes, web data APIs and browser agents behind one API and one credit balance.
Its main product is a cloud Chrome session you drive with Playwright or Puppeteer, with stealth mode, residential proxies, CAPTCHA solving, saved profiles and recordings. Next to it Hyperbrowser sells Sandboxes, Firecracker VMs on Ubuntu 24.04 that live up to 24 hours, with memory snapshots, volumes and outbound rules, plus Fetch, Scrape and Search APIs and hosted browser agents. It is a browser and web data platform more than a general sandbox, so this page compares where it overlaps with boat: agents that browse, and agents that run code.
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 | Hyperbrowser: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Hyperbrowser's sandbox docs do not cover Docker inside the VM, and its disk goes away on stop, so builds that need containers fit boat better. | 3rd cheapest of 367 $634 a month | 136th of 367, with limits $1,206 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month hits Hyperbrowser's 24-hour sandbox lifetime; boat has no session cap on paid plans. | 5th cheapest of 366 $657 a month | 255th of 366, with limits $3,650 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Neither is a perfect fit; Hyperbrowser's memory snapshots start new sandboxes from a warm state, which suits many short code runs. | 186th of 345, with limits $2,000 a month | 244th of 345, with limits $246 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 | 245th of 361, with limits $1,029 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 | 262nd of 360, with limits $4,972 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 | 253rd of 364, with limits $400 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs often need Docker or an emulator; boat has Docker and /dev/kvm, which Hyperbrowser's sandbox docs do not document. | 4th cheapest of 377 $86 a month | 238th of 377, with limits $120 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 18th cheapest of 368 $26 a month | 240th of 368, with limits $73 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Hyperbrowser runs computer-use models inside its browser, while boat streams a 60fps Linux desktop where the agent can use any app, not only Chrome. | 6th cheapest of 369 $200 a month | 144th of 369, with limits $360 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit: Hyperbrowser gives a stealth Chrome over CDP with proxies and CAPTCHA solving, and boat gives Chromium on a full VM where the agent can also run code. | 7th cheapest of 367 $200 a month | 20th cheapest of 367 $360 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; Hyperbrowser also sells Fetch and Scrape APIs per page, so you may not need a browser at all. | 6th cheapest of 346 $90 a month | 32nd cheapest of 346 $366 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Hyperbrowser fits mass scraping better: residential proxies, stealth modes and CAPTCHA solving come with its paid plans, while boat uses datacenter IPs and solves no CAPTCHAs. | 71st of 338, with limits $1,800 a month | 11th of 338, with limits $9,750 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 | 33rd of 360, with limits $356 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 | Hyperbrowser |
|---|---|---|
| Kind of product | A full Linux VM per sandbox, with a desktop and Chromium inside | Cloud browser sessions first, plus Firecracker sandboxes and web data APIs |
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Firecracker VM per sandbox; browser sessions are isolated, technology not published |
| Machine size | 4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB by plan | Sandboxes up to 32 vCPU and 256 GiB RAM, disk up to 32 GiB; browser size not published |
| Session length | No cap on paid plans; you set the time to live | Sandboxes up to 24 hours from VM start; browsers up to 12 hours |
| Files after a stop | The disk persists, with snapshots every minute and on stop; a stopped sandbox costs nothing | A stopped sandbox is gone; files survive on a mounted volume or in a memory snapshot you take |
| Memory snapshots and fork | Fork a running sandbox with its disk; no memory snapshots | Memory snapshot of a running sandbox, then start many new sandboxes from it instantly |
| Docker and nested virtualization | Docker, systemd and /dev/kvm on every machine | Docker is used to build images on your machine; Docker or /dev/kvm inside a sandbox is not documented |
| Shell access | SSH and root on every machine | Exec, process and PTY terminal APIs through the SDK; sudo user; no SSH |
| Browser and computer use | 60fps desktop and Chromium, computer use and browser control, embeddable stream | Cloud Chrome over CDP with live view and recordings; hosted HyperAgent, Browser Use and computer-use models |
| Bot detection | Datacenter IPs and Chromium; no CAPTCHA solving | Stealth mode, residential proxies and CAPTCHA solving on paid plans; ultra stealth on Enterprise |
| Reaching the machine | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 | HTTPS URL per exposed port, public or token-protected, through a shared regional proxy; no raw TCP or own IP |
| Outbound rules | Open internet, no provider-side allowlist | Default-deny or allow by domain, IP or CIDR; deny by IP or CIDR; changeable while the VM runs |
| Coding agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | Base images with the Claude Code, Codex or OpenClaw CLI installed, run through the exec API |
| 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 | Keys are passed in as environment variables to the process |
| Compliance and transparency | SOC 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)
| Feature | boat | Hyperbrowser |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | No |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | No |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | Yes |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | Yes |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | No |
| Public IPv4 | No | No |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | Yes |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | Not published |
| 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 | Yes |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | No |
| HIPAA | No | Not published |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. Hyperbrowser was not in StarSling's public CPU benchmark, so there is no number to set against boat's 26.69 runs per second at 4 vCPU / 8 GB. Hyperbrowser publishes start times of under 50 ms for sandboxes and under 500 ms for a ready browser.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Hyperbrowser 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 | Hyperbrowser, 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 | $16 · Free · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $73 · Free · 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 | $792 · Scale · 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 | $450 · Scale · 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 | $994 · Scale · 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.
Hyperbrowser: Everything spends one credit balance at $0.001 a credit: browsers cost $0.10 a browser-hour plus $10 per GB of proxy data, and sandboxes cost $0.045 per vCPU-hour plus $0.015 per GiB-hour while the VM runs. Startup ($30) and Scale ($100) turn their monthly fee into credits that reset each month; extra credits are bought by hand or by auto-reload.
Limits in those scenarios
The Hyperbrowser prices in the table are for its browser session at $0.10 an hour, with no published size and no disk that stays, so none of them is a 4 vCPU / 8 GB machine. Its sandboxes are a closer match but are billed per vCPU and GiB, lose their disk when they stop and live at most 24 hours, so an always-on agent has to be rebuilt every day. Concurrency is the other limit: 100 browsers at once on Scale, so 300 sessions for your users and 1,000 short jobs at once need Enterprise; sandbox concurrency limits are not published. 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 | Hyperbrowser |
|---|---|---|
| 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 Hyperbrowser when
your agent mainly needs the web: stealth browsing behind CAPTCHAs with residential proxies, fetch and search APIs, short sandboxes started from memory snapshots, or regions in the US.
- Stealth browsing and web data APIs. Useful for scraping sites that block bots: residential proxies, stealth modes and CAPTCHA solving come built in, plus per-page fetch and search APIs.
- Memory snapshots, outbound rules and big machines. Useful for many short code runs from a warm state, behind a default-deny network, on machines up to 32 vCPU and 256 GiB.
- US regions. Useful if your users or target sites are in North America: three US regions, Europe, and Asia on Enterprise.
Use boat when
your agent browses and also works: installs, builds, Docker and dev servers on a full VM that keeps its disk and runs as long as the task takes, with coding agents and a key proxy built in.
- One machine that keeps running and keeps its files. An agent that works across days on Hyperbrowser has to be rebuilt every 24 hours from a snapshot or volume, and anything it wrote outside the volume before a crash or timeout is lost.
- Docker, systemd and /dev/kvm on a full VM. Agents that run docker compose, test against a database container or boot an Android emulator need these inside the machine. Without them the agent stops at the first step of many real repos.
- Coding agents you drive from outside, keys kept outside. On Hyperbrowser you write the agent harness and pass the model key in as an environment variable, where a prompt-injected agent can read and leak it.
Questions people ask
Is boat cheaper than Hyperbrowser?
The table sets a 4 vCPU / 8 GB boat VM against a Hyperbrowser browser session that keeps no disk. 50 agents in parallel come to $317 on boat against $792, and sandboxes for your users to $200 against $450. Hyperbrowser's free credits cover the workday scenario but without a disk, and for 1,000 short jobs at once neither fits.
Can a Hyperbrowser sandbox run Docker?
Hyperbrowser uses Docker on your own machine to build a custom image, which then runs as a Firecracker VM. Its docs do not describe running Docker inside a sandbox. Every boat sandbox runs Docker, systemd and /dev/kvm out of the box.
How long can a Hyperbrowser sandbox run?
Up to 24 hours from VM start, and browser sessions up to 12 hours. When a sandbox stops, files survive only on a mounted volume or in a memory snapshot. boat has no session cap on paid plans and keeps the disk when you stop.
Does boat have stealth mode or CAPTCHA solving like Hyperbrowser?
No. boat runs Chromium on datacenter IPs and does not solve CAPTCHAs. For scraping sites that block bots at volume, Hyperbrowser's residential proxies, stealth modes and CAPTCHA solver are built for that.
Can I use boat and Hyperbrowser together?
Yes. An agent on a boat sandbox can open a Hyperbrowser session over CDP or call its fetch API, and keep its code, files and tools on the boat VM. That puts stealth browsing on Hyperbrowser and the rest of the work on a machine that keeps its disk.
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
More comparisons
- boat vs Browser Use
- boat vs Notte
- boat vs Kernel
- boat vs Zenrows
- boat vs Anchor Browser
- boat vs Scrapeless
- boat vs Steel
- boat vs BrowserCloud
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- Browserbase vs Hyperbrowser
- Browser Use vs Hyperbrowser
- Steel vs Hyperbrowser
- Hyperbrowser vs Kernel
- Hyperbrowser vs Anchor Browser
- Hyperbrowser vs Browserless
- Hyperbrowser vs Notte
- Hyperbrowser vs Scrapeless