boat vs Anchor Browser
Anchor Browser rents you a managed Chromium in its cloud, with stealth, proxies and logins handled for you. boat gives your agent a whole Linux machine with a browser and desktop inside, where it can also run code, Docker and servers and keep its files.
Where boat stands out
A whole machine around the browser
A boat sandbox is a full Linux VM with root, a shell, Docker and systemd, and Chromium and a desktop already inside. Your agent can browse a site, save what it found, run a script on it, build an app and serve it, all on one machine.
Nothing is wiped when the job ends
On boat 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 agent comes back to the same files, tools and browser profile.
A real desktop and coding agents you drive
boat streams a full Linux desktop at 60fps that you can embed, so a computer-use agent can open any app, not only web pages. Claude Code, Codex and other coding agents come preinstalled, you prompt, steer and follow them through one API, and a credentials proxy keeps real API keys outside the sandbox.
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
Anchor Browser
Anchor Browser is cloud browser infrastructure for AI agents: managed Chromium sessions you control over CDP or a REST API, plus a hosted browser agent.
Anchor Browser is a different kind of product from boat. Each session is a headful Chromium in its own VM that is erased when the session ends, and you drive it with Playwright or Puppeteer, with mouse and keyboard calls, or by sending a task in plain words to its hosted agent. It adds managed logins with MFA, residential proxies, stealth and CAPTCHA solving, and its own docs tell you to run your agent's code in a separate sandbox and connect to the browser over CDP.
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 | Anchor Browser: 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; Anchor's own docs send that code to a separate sandbox. | 3rd cheapest of 367 $634 a month | 180th of 367, with limits $2,000 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that runs all month needs a machine that keeps its state; Anchor keeps only browser profiles and volume files between sessions. | 5th cheapest of 366 $657 a month | 71st of 366, with limits $1,845 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 | 325th of 345, with limits $2,171 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month 300 sandboxes for your users is more than Anchor's Growth plan allows at once (200 browsers), and each one is a browser, not a machine. | Cheapest of 361 $209 a month | 283rd of 361, with limits $2,000 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 | 298th of 360, with limits $12,510 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 | 357th of 364, with limits $2,000 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 | 284th of 377, with limits $500 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box needs SSH and a shell, and an Anchor session exposes only CDP and a live view. | 18th cheapest of 368 $26 a month | 222nd of 368, with limits $42 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Anchor's mouse and keyboard calls act inside the browser session; boat streams a full Linux desktop at 60fps, so agents can use apps beyond the browser. | 6th cheapest of 369 $200 a month | 173rd of 369, with limits $500 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month This is what Anchor Browser is built for: browser tasks on sites that need logins, proxies or stealth; boat fits too when the agent also needs a shell, files or code. | 7th cheapest of 367 $200 a month | 28th cheapest of 367 $560 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; boat gives each bot a whole machine whose disk keeps its files, while Anchor erases the browser's VM after every session. | 6th cheapest of 346 $90 a month | 50th cheapest of 346 $500 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Mass scraping of sites with strong bot checks needs residential IPs, stealth fingerprints and CAPTCHA solving, which Anchor includes and boat does not. | 71st of 338, with limits $1,800 a month | 5th of 338, with limits $6,175 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 | 334th of 360, with limits $2,000 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 | Anchor Browser |
|---|---|---|
| What you get | A full Linux VM with its own kernel and root, on dedicated AMD Ryzen 9 9950X hosts | A managed headful Chromium in its own VM, reached over CDP or Anchor's API |
| Shell, code and Docker | SSH, any language, Docker, systemd and nested virtualization (/dev/kvm) | No shell; from Growth you can run TypeScript snippets against the page |
| State after a session | The whole disk is saved every minute and on stop; fork a running sandbox | The VM is erased; profiles keep cookies, local storage and cache, and up to 10 volumes keep files |
| Session length | No cap on paid plans; a stopped sandbox keeps its disk | 180 minutes by default with no upper limit if you raise it; ends after 5 idle minutes by default |
| Desktop and live view | A full Linux desktop streamed at 60fps, or Chromium alone; embed it in your app | Embeddable live view of the browser, with mouse, keyboard and screenshot calls |
| Stealth and CAPTCHAs | Chromium on datacenter IPs; no fingerprint rotation or CAPTCHA solving | CAPTCHA solving from Starter; full stealth Chromium on Growth; unique fingerprints on Enterprise |
| Proxies | None managed; you can run your own proxy client inside the VM | Residential proxies with country and city targeting, sticky IPs, or your own proxy |
| Logging in to sites | Your agent logs in itself; boat switches AI credentials to another account when credits run out | Managed identities with MFA keep logins across sessions, from Starter |
| Agents | Claude Code, Codex and other coding agents preinstalled, with a prompt, steer and events API | Hosted browser agents (browser-use, OpenAI, Gemini and Anthropic computer use) with human-in-the-loop and webhooks |
| Keeping secrets from the agent | Credentials proxy: real keys never enter the sandbox, for any HTTPS API | Secret values are hidden from the model and typed into the page |
| Hosting | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP | No ports of your own; only the CDP socket and the live view URL |
| Outbound rules | Open internet; you can add firewall rules inside the VM | Allowlists of domains enforced at the browser |
| Regions | EU only (Germany, Finland, France) | US by default; EU, Asia and Australia on Growth; your own cloud or on-premise on Enterprise |
| 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 | Anchor Browser |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | No |
| Systemd | Yes | No |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | Yes |
| 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 | No |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | Yes |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | No |
| 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 | No |
| Self-hosting | No | Yes |
| BYOC | No | Yes |
| 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 | 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. Anchor sells browser-hours and does not publish the CPU or memory behind each browser, and it 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. Anchor Browser 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 | Anchor Browser, 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 | $7 · Free · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $42 · 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 | $500 · Team · 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 | $2,000 · Growth · 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 | $2,510 · Growth · 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.
Anchor Browser: Anchor bills $0.05 per browser-hour of active session time, counted to the nearest minute, plus $0.01 for each browser created. Plan fees (Starter $50, Team $500, Growth $2,000) become credits worth $1 each, and traffic is extra: $8 per GB through Anchor's proxy or $0.20 per GB direct, with AI tasks priced per step on top.
Limits in those scenarios
None of the five scenarios fits Anchor Browser as written, because each one asks for a general machine and Anchor sells a browser session with no shell, of a size it does not publish. Its plans also cap browsers at once (25 on Starter, 50 on Team, 200 on Growth), so 300 sandboxes for your users and 1,000 short jobs at once go past Growth into Enterprise. Sessions end after 180 minutes and after 5 idle minutes unless you raise those limits, and the machine is erased each time. boat fits four scenarios; at 1,000 short jobs at once its $2,000 plan queues the starts.
| Scenario | boat | Anchor Browser |
|---|---|---|
| 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 Anchor Browser when
your agents only need a browser and the hard part is the website: logins with MFA, residential proxies, stealth and CAPTCHAs, handled for you.
- Built to get past bot checks. For sites with strong bot checks: stealth Chromium, CAPTCHA solving and residential proxies with country and city targeting.
- Logins and browser agents as a service. For teams that want to send a task and get a result: managed logins with MFA, hosted browser agents and a hosted MCP server.
- US and other regions, or your own cloud. Runs in the US by default, adds EU, Asia and Australia on Growth, and offers your own cloud or on-premise on Enterprise.
Use boat when
your agent does more than browse: it needs a shell, files, Docker, a desktop or a server next to the browser, and it has to keep its work between runs.
- A whole machine around the browser. Anchor's own docs say to run your agent's code in a separate sandbox and reach the browser over CDP. That is two services to pay for and wire together, and every download has to cross between them.
- Nothing is wiped when the job ends. Each Anchor session VM is erased when it ends. Profiles carry cookies and cache and volumes carry files, but installed tools and anything else on the machine start over each time.
- A real desktop and coding agents you drive. Anchor's agents act inside a browser, and its secrets are typed into the page, where the browser can read them. An agent that also writes code or calls APIs needs its keys kept somewhere it cannot reach.
Questions people ask
Is Anchor Browser a sandbox like boat?
No. Anchor gives you a managed Chromium in its own VM that you drive over CDP or its API, with no shell on the machine. Its docs say to run your agent's code in a separate sandbox. 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 Anchor Browser?
It depends on the scenario. One coding agent on workdays costs $20 on boat and $7 of browser time on Anchor, but one agent running all month costs $26 against $42, 50 agents in parallel $317 against $500, and 300 sandboxes for your users $200 against $2,000. Anchor fits none of them as a general machine, and proxy traffic and AI steps are billed on top.
Can I use Anchor Browser from a boat sandbox?
Yes. Anchor's docs describe exactly this: your code runs in a sandbox and connects to an Anchor browser over HTTPS and CDP with its npm or PyPI SDK. You can run that code on boat and keep Chromium on boat for the pages that need no stealth.
How long can an Anchor Browser session run?
By default a session ends after 180 minutes, or 5 minutes after the last connection closes. You can raise the maximum with no upper limit and turn the idle timeout off. When it ends, its VM is erased; a boat sandbox has no session cap on paid plans and keeps its disk when it stops.
Which one is better at getting past bot checks?
Anchor Browser. It solves CAPTCHAs, offers a full stealth Chromium on Growth, and routes traffic through residential proxies you can target by country and city. 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
More comparisons
- boat vs Browser Use
- boat vs Notte
- boat vs Kernel
- boat vs Zenrows
- boat vs Scrapeless
- boat vs Hyperbrowser
- boat vs Steel
- boat vs BrowserCloud
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- Browserbase vs Anchor Browser
- Browser Use vs Anchor Browser
- Steel vs Anchor Browser
- Hyperbrowser vs Anchor Browser
- Kernel vs Anchor Browser
- Anchor Browser vs Browserless
- Anchor Browser vs Notte
- Anchor Browser vs Scrapeless