boat vs Browserless
Browserless is a browser API: headless Chrome, Firefox and WebKit you drive with Puppeteer, Playwright or BrowserQL, with stealth, CAPTCHA solving and proxies. boat gives each agent one full Linux VM with root, Docker and a disk that persists, plus a 60fps desktop with Chromium and coding agents you drive from outside.
Where boat stands out
A whole machine, not only a browser
Every boat sandbox is a full VM with root, SSH, systemd, Docker and nested virtualization, on dedicated AMD Ryzen 9 9950X hosts, with Chromium on a desktop inside it. A Browserless session gives your code a browser over CDP, BrowserQL or REST, and nothing else on the machine.
Runs as long as the task, keeps its disk
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 Browserless session ends after at most 60 minutes on Scale, and only cookies, localStorage and cache can be kept for the next one.
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. Browserless runs its own managed browser agent in beta, capped at 15 minutes and 60 steps a turn. 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
Browserless
Browserless calls itself a cloud browser automation platform: managed headless browsers you connect to with one line of code.
You point existing Puppeteer, Playwright or Selenium code at a Browserless WebSocket URL, or use BrowserQL, its GraphQL language with stealth and CAPTCHA solving, REST endpoints for screenshots, PDFs and scraping, and an MCP server. Sessions are short (2 to 60 minutes by plan), and only the browser profile can be kept between them. It is a browser product, not a general sandbox: you get a browser, not a shell or root on the machine, so this page compares where the two overlap, which is agents that browse.
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 | Browserless: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent needs a shell, Docker and a disk, and a Browserless session gives a browser only, so builds and tests fit boat. | 3rd cheapest of 367 $634 a month | 170th of 367, with limits $1,771 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month hits Browserless's 60-minute session cap and keeps only a browser profile between sessions; boat has no session cap on paid plans. | 5th cheapest of 366 $657 a month | 297th of 366, with limits $6,170 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 | 267th of 345, with limits $350 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 | 264th of 361, with limits $1,490 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 | 279th of 360, with limits $8,600 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 | 247th of 364, with limits $350 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs need a shell, Docker and often /dev/kvm, which boat has and a browser session does not. | 4th cheapest of 377 $86 a month | 241st of 377, with limits $140 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box has to keep its files and processes, and a Browserless session starts a new browser process on each reconnect, so this fits boat. | 18th cheapest of 368 $26 a month | 336th of 368, with limits $350 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Browserless agents act on web pages only, while boat streams a 60fps Linux desktop where an agent can use any app, not only a browser. | 6th cheapest of 369 $200 a month | 141st of 369, with limits $350 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit: Browserless gives a managed headless browser over Puppeteer, Playwright or BrowserQL, and boat gives Chromium on a full VM where the same agent can also run code. | 7th cheapest of 367 $200 a month | 19th cheapest of 367 $350 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; Browserless also has REST endpoints for screenshots, PDFs and scraping, so some pages need no script at all. | 6th cheapest of 346 $90 a month | 47th cheapest of 346 $478 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Browserless fits mass scraping better: BrowserQL stealth, CAPTCHA solving and residential proxies are built for sites that block bots, while boat uses datacenter IPs. | 71st of 338, with limits $1,800 a month | 20th of 338, with limits $17,150 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 | 247th of 360, with limits $350 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 | Browserless |
|---|---|---|
| Kind of product | A full Linux VM per sandbox, with a desktop and Chromium inside | Managed headless Chrome, Firefox and WebKit, plus BrowserQL, REST APIs and an MCP server |
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Browsers in Docker containers that share the host kernel |
| What the agent can touch | The whole machine: root, SSH, any package, any process | The browser, over CDP, BrowserQL or REST; no shell or SSH |
| Docker and nested virtualization | Docker, systemd and /dev/kvm on every machine | Not offered in a session; you can self-host the Browserless Docker image on your own machines |
| Session length | No cap on paid plans; you set the time to live | 2 minutes on Free, 15 on Prototyping, 30 on Starter, 60 on Scale |
| Files after a session | The disk persists, with snapshots every minute and on stop; a stopped sandbox costs nothing | Persisted sessions keep cookies, localStorage and cache for 1 to 90 days by plan; a new browser process starts on reconnect |
| Fork | Fork a running sandbox with its disk | No fork; many sessions can start from one saved profile, each with its own copy |
| Browser and computer use | 60fps desktop and Chromium, computer use on any app, embeddable stream | Headless browsers, live URLs that hand a session to a person, and computer-use integrations |
| Bot detection | Datacenter IPs and Chromium; no CAPTCHA solving | BrowserQL stealth with fingerprint mitigations, CAPTCHA solving, residential and datacenter proxies |
| Reaching the machine | HTTPS URLs for up to 50 ports, token-protected; raw TCP; own IP | Fixed regional WebSocket and HTTPS endpoints and short-lived live URLs; no ports to host on |
| Agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | Its own managed browser agent (Agent Run API, beta), up to 15 minutes and 60 steps per turn |
| 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 | 1Password integration fills logins into the page without the value reaching your code |
| Self-hosting | Hosted only | Run the open source Docker image yourself; commercial use needs a license |
| Regions | EU only (Germany, Finland and France) | San Francisco, London and Amsterdam; New York on private fleets |
| 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 | Browserless |
|---|---|---|
| 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 | Yes |
| 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 | No |
| Idle auto-stop | No | Yes |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | Not published |
| 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 | Yes |
| Windows | No | No |
| Arm64 | No | No |
| Self-hosting | No | Yes |
| BYOC | No | Yes |
| Open source | No | Yes |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. Browserless was not in StarSling's public CPU benchmark, and it does not publish the vCPU or RAM behind a browser session, so there is no number to set against boat's 26.69 runs per second 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. Browserless 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 | Browserless, 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 | $350 · Scale annual · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $350 · Scale annual · 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 | $1,026 · Scale annual · 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 | $410 · Scale annual · 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 | $1,400 · Scale annual · 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.
Browserless: Browserless bills in units: one unit is up to 30 seconds of a connected browser, and a reconnect starts a new block. Plans include 20,000, 180,000 or 500,000 units a month, then $0.0020 to $0.0015 a unit; proxy traffic and CAPTCHA solves use the same units, and annual billing is 30% lower and adds concurrency.
Limits in those scenarios
The Browserless prices in the table are for its browser session, with no published size and no disk that stays, so none of them is a 4 vCPU / 8 GB machine. The 60-minute session cap on Scale is why the workday agent, the always-on agent and the 50-agent fleet do not fit. Concurrency is the other limit: 100 at once on Scale annual, so 300 sandboxes for your users and 1,000 short jobs at once need Enterprise through sales. 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 | Browserless |
|---|---|---|
| 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 Browserless when
your agent only needs the web: headless browsers on short sessions, stealth, CAPTCHA solving and residential proxies for sites that block bots, a Docker image you can run yourself, or browsers in the US.
- Getting past bot walls. Useful for scraping sites that block bots: BrowserQL stealth, fingerprint mitigations, CAPTCHA solving and residential proxies.
- Run it on your own machines. Useful if browsers must run inside your own network: the Browserless Docker image is open source and can be self-hosted.
- A browser API ready to use, in the US too. Useful when the job is only the web: REST screenshots and PDFs, live hand-off to a person, and a San Francisco region.
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.
- A whole machine, not only a browser. An agent that reads a page and then has to clone a repo, run docker compose or start a dev server needs a second provider next to Browserless, and has to move files between the two.
- Runs as long as the task, keeps its disk. A browsing job longer than an hour on Browserless has to be split into sessions, each with a new browser process, and downloads or notes outside the browser profile are gone each time.
- Coding agents you drive from outside, keys kept outside. On Browserless you either use its beta agent as it is or write your own harness around a session, and the API keys your agent uses have to live in your own code.
Questions people ask
Is boat cheaper than Browserless?
The table sets a 4 vCPU / 8 GB boat VM against a Browserless browser session that keeps no disk. One coding agent on workdays comes to $20 a month on boat against $350, and 50 agents in parallel to $317 against $1,026. For 1,000 short jobs at once neither fits, and Browserless is lower there at $1,400 against $2,000.
Can Browserless run Docker or a shell?
A hosted Browserless session gives you a browser over CDP, BrowserQL or REST, not a shell on the machine. You can run the Browserless Docker image on your own server, but that is your machine, not theirs. Every boat sandbox has root, SSH, Docker, systemd and /dev/kvm.
How long can a Browserless session run?
2 minutes on Free, 15 on Prototyping, 30 on Starter and 60 on Scale, with custom limits on Enterprise. A persisted session keeps cookies, localStorage and cache for up to 90 days, but a new browser process starts on each reconnect. boat has no session cap on paid plans and keeps the disk when you stop.
Does boat have stealth or CAPTCHA solving like Browserless?
No. boat runs Chromium on datacenter IPs and does not solve CAPTCHAs. For sites that block bots at volume, Browserless's BrowserQL stealth, CAPTCHA solving and residential proxies are built for that.
Can I use boat and Browserless together?
Yes. An agent on a boat sandbox can connect to a Browserless session over WebSocket, or call its REST and MCP tools, and keep its code, files and tools on the boat VM. That puts protected browsing on Browserless 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 Hyperbrowser
- boat vs Steel
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- Browserbase vs Browserless
- Browser Use vs Browserless
- Steel vs Browserless
- Hyperbrowser vs Browserless
- Kernel vs Browserless
- Anchor Browser vs Browserless
- Browserless vs Notte
- Browserless vs Scrapeless