boat vs Browserbase
Browserbase is a browser platform: cloud Chrome sessions with proxies, CAPTCHA solving and session replay, each in a fresh VM that is destroyed at the end. A saved Context brings the browser profile back. boat gives each agent one full Linux VM with root and Docker. Its disk is saved every minute and kept at least 14 days after a stop. It has a 60 fps desktop with Chrome 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, with Chrome on a desktop inside it. A Browserbase session gives your code a Chrome over CDP. Its hosted Agent and Functions have a shell, but in a short TypeScript runtime with no persistent storage.
Runs as long as the task, keeps its disk
With auto-stop off, a boat sandbox has no session cap on paid plans (auto-stop defaults to 1 hour). Its disk is saved every minute and at each stop, and kept at least 14 days after a stop. A stopped sandbox has no compute charge. Memory and running processes are not saved. A Browserbase session ends after at most 6 hours on self-serve plans, its VM is rebuilt from scratch, and a Context keeps the browser profile.
Coding agents you drive from outside, keys kept outside
boat ships seven coding-agent harnesses, such as Claude Code, Codex and OpenCode, in each sandbox. You prompt, steer and follow them through one API with an event stream. Browserbase runs its own browser Agent with its own tools. With boat's optional paid credentials proxy on, real keys for model providers and custom HTTPS APIs stay 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
Browserbase
Browserbase calls itself the complete platform to build and deploy agents that browse and interact with the web like humans: browsers, search, fetch, functions, model access and identity behind one API key.
Its core product is a Chrome session you drive over CDP with Playwright, Puppeteer or its open source Stagehand SDK, with proxies, CAPTCHA solving, saved browser profiles (Contexts), live view and session replays. Around it sit Search and Fetch APIs (Authenticated Fetch reads logged-in pages without a browser), short TypeScript Functions, Runtime (sandboxed environments that back the hosted Agent shell), a Model Gateway and hosted Agents that work from a plain language goal. It is a browser platform, not a general VM: your code gets the browser, and the Agent gets a shell in a short-lived runtime, not root on a machine. 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. “5th cheapest of 365” means 4 of the other 364 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 | Browserbase: 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. A Browserbase session gives a browser, and its Agent shell runs in a short-lived runtime without Docker, so builds and tests fit boat. | 5th cheapest of 365 $634 a month | 172nd of 365, with limits $1,255 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month hits the 6-hour session cap on self-serve plans, and only the browser profile and saved downloads carry over. boat has no session cap once auto-stop is off (paid plans; default 1 hour). | 6th cheapest of 361 $657 a month | 286th of 361, with limits $3,699 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 189th of 336, with limits $2,000 a month | 267th of 336, with limits $382 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month | 3rd cheapest of 349 $209 a month | 245th of 349, with limits $1,099 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 39th of 349, with limits $2,000 a month | 259th of 349, with limits $5,049 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 10th cheapest of 359 $200 a month | 346th of 359, with limits $449 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. | 2nd cheapest of 374 $86 a month | 245th of 374, with limits $152 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box has to keep its files. Each Browserbase session starts on a fresh VM, and a Context brings back only the browser profile, so this fits boat. boat keeps the disk, not running processes: a resume is like a reboot. | 19th cheapest of 371 $26 a month | 264th of 371, with limits $96 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Browserbase agents act on web pages through Stagehand, while boat streams a 60fps Linux desktop where an agent can use any app, not only Chrome. | 7th cheapest of 367 $200 a month | 199th of 367, with limits $416 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit: Browserbase gives a managed Chrome over CDP with proxies, CAPTCHA solving and replays, and boat gives Chrome on a full VM where the same agent can also run code. | 7th cheapest of 356 $200 a month | 23rd cheapest of 356 $449 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; Browserbase also sells Fetch and Search APIs per call, so some pages need no browser at all. | 6th cheapest of 343 $90 a month | 59th cheapest of 343 $537 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Browserbase fits mass scraping better: residential proxies in 200+ countries, CAPTCHA solving and Verified browsers are built for sites that block bots. boat uses datacenter IPs and has no built-in proxies. | 73rd of 327, with limits $1,800 a month | 12th of 327, with limits $9,799 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 3rd cheapest of 351 $200 a month | 259th of 351, with limits $291 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | boat | Browserbase |
|---|---|---|
| Kind of product | A full Linux VM per sandbox, with a desktop and Chrome inside | Managed headless Chrome sessions, plus search, fetch, functions and hosted browser agents |
| Isolation | Full VM with its own kernel; vCPUs are shared, not dedicated cores | 1 browser per VM in its own subnet; the VM is destroyed after each session |
| What the agent can touch | The whole machine: root, SSH, any package, any process | The browser over CDP; the hosted Agent and Functions get a shell in a short-lived sandboxed runtime without root |
| Docker and nested virtualization | Docker, systemd and /dev/kvm on every machine | No Docker or /dev/kvm documented in sessions, Functions or the Agent runtime |
| Session length | No cap once auto-stop is off (paid plans); auto-stop defaults to 1 hour and can be set up to 30 days | 6 hours on Developer and Startup, 6+ hours on Scale, 15 minutes on Free; Functions up to 900 seconds |
| Files after a session | The disk is saved every minute and at each stop, and kept at least 14 days after a stop; memory, processes and /tmp are not saved | The browser profile carries over in a Context; downloads go to Browserbase storage and you fetch them with the Downloads API; no other files carry over |
| Fork | Fork a running sandbox from its last 1-minute snapshot (writes from the last minute can be missing) | No fork documented; many new sessions can load the same saved Context |
| Browser and computer use | 1920x1080, 60 fps desktop and Chrome, computer tools on any app, embeddable stream | Chrome with live view, session replay and logs; Stagehand act, extract and observe |
| Bot detection | Datacenter IPs; no built-in residential proxies or CAPTCHA solving | Residential proxies in 200+ countries, CAPTCHA solving on paid plans, Verified browsers on Scale |
| Reaching the machine | HTTPS URLs for up to 50 ports, token-protected; raw TCP to the sandbox IP (IPv6 only on some sandboxes; the IP changes at each resume) | CDP connect URL and live view links only; no ports to host on |
| Outbound rules | Open internet; no provider-side allowlist (you set up a firewall yourself with root on the VM) | Navigation Policies allow or block site categories and domains for page loads, iframes, popups and redirects (enabled by support); an experimental allowedDomains list also exists |
| Agents | Seven coding-agent harnesses preinstalled (Claude Code, Codex, OpenCode and more), with a prompt, steer and events API | Its own hosted browser Agent from a plain language goal, with its own built-in tools; runs can pause for human steps such as MFA |
| Keeping keys out of the sandbox | Optional paid AI credentials proxy ($1 a day it is on, plus $1 per 1,000 requests) for model providers and custom HTTPS APIs; other secrets still enter the sandbox | Model Gateway for OpenAI, Anthropic and Google; Secrets in Functions; 1Password fills logins without showing the password to the app or model |
| Regions | Germany, Finland and France; you cannot pick a region; no US or Asia region | Oregon, Virginia, Frankfurt and Singapore |
| 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 | Browserbase |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | No documented way |
| Nested virtualization | Yes | No documented way |
| Root | Yes | No documented way |
| Systemd | Yes | No documented way |
| Desktop GUI | Yes | No documented way |
| Browser | Yes | Yes |
| Computer-use API | Yes | No documented way |
| SSH | Yes | No documented way |
| Persistent disk | Yes | No documented way |
| Pause/resume | Yes | No documented way |
| Automatic snapshots | Yes | No documented way |
| Fork/clone | Yes | No documented way |
| Live fork (no pause) | Yes | No documented way |
| Memory fork | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | No documented way |
| ≥24 h sessions | Yes | No documented way |
| Idle auto-stop | No documented way | Yes |
| Wake on request | No documented way | No documented way |
| HTTPS preview URLs | Yes | No documented way |
| Raw TCP inbound | Yes | No documented way |
| Public IPv4 | No documented way | No documented way |
| Egress allowlist | No documented way | Yes |
| Secret proxy | Yes | Yes |
| Secret proxy for any API | Yes | No documented way |
| Preinstalled agents | Yes | Yes |
| Agent harness API | Yes | No documented way |
| MCP server | No documented way | Yes |
| GPU | No documented way | No documented way |
| Windows | No documented way | No documented way |
| Arm64 | No documented way | No documented way |
| Self-hosting | No documented way | No documented way |
| BYOC | No documented way | No documented way |
| Open source | No documented way | No documented way |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | Not published |
| Audit logs | No documented way | Not published |
| SSO | No documented way | Yes |
| SOC 2 | No documented way | Yes |
| HIPAA | No documented way | Yes |
| EU data residency | No documented way | Yes |
| Zero data retention | Yes | Yes |
Performance
Browserbase is not in the public benchmarks we use, and it does not publish the vCPU or RAM behind a browser session, so we cannot say which is faster.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Browserbase is not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | boat, a month | Browserbase, 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 | $99 · Startup · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $122 · Startup · 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 | $841 · Startup · 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 | $499 · Startup · with limits |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $8,800 · $2000/mo · with limits | $1,049 · Startup · with limits |
boat: You pick a monthly plan from $20. The plan price comes back as VM time for that month: $20 is about 555 hours of a 4 vCPU / 8 GB sandbox, billed per second. The $20 plan runs 100 sandboxes at once and includes 12 starts a minute, 60 an hour and 200 a day. Create, fork and resume each count as one start; a resume onto the kept machine does not count. Extra starts cost $0.03 to $0.07 each, up to 1,200 a day, and starts above that fail. A stopped sandbox uses no machine time and keeps its disk for at least 14 days. Saved snapshots above the included count and the AI credentials proxy still cost money.
Browserbase: Plans include browser hours: 100 on Developer ($20) and 500 on Startup ($99), then $0.12 or $0.10 per browser hour, billed by the minute with a one-minute minimum per session. Proxy data is extra after 1 GB or 5 GB ($12 or $10 per GB), and Search, Fetch and Agents calls have their own allowances. Free gives 1 browser hour a month with 15-minute sessions. Scale has no public price.
Limits in those scenarios
The Browserbase prices in the table are for its browser session, with no published size and no disk, so none of them is a 4 vCPU / 8 GB machine. The 6-hour session cap on self-serve plans is why the always-on agent and the workday agent do not fit, and a keepAlive session keeps billing until you release it. Concurrency is the other limit: 100 at once on Startup, so 300 sandboxes for your users and 1,000 short jobs at once need Scale, which has no public price. On boat, the 1,000-job burst does not fit either: on the $2,000 plan, starts above 90 a minute are paid, starts above 270 a minute fail with 429, and boat never queues a start. boat auto-stop defaults to 1 hour, and the IP address changes at each resume.
| Scenario | boat | Browserbase |
|---|---|---|
| One coding agent, workdays | None for this scenario |
|
| One agent that never stops | None for this scenario |
|
| 50 agents in parallel | None for this scenario |
|
| Sandboxes for your users | None for this scenario |
|
| 1,000 short jobs at once |
|
|
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Which one should you use?
Use Browserbase when
your agent only needs the web: hosted Chrome at scale, residential proxies and CAPTCHA solving for sites that block bots, saved logins, session replays, or browsers in the US and Singapore.
- Getting past bot walls. Useful for scraping sites that block bots: residential proxies in 200+ countries, CAPTCHA solving and Verified browsers with real fingerprints.
- A browser stack ready to use. Useful when the job is only the web: open source Stagehand, Search and Fetch APIs, saved logins, 1Password sign-in, live view and replays of every session.
- US and Asia regions. Useful if your users or target sites are in North America or Asia: Oregon, Virginia, Frankfurt and Singapore.
- Outbound rules per site. Useful when an agent must stay on approved sites: Navigation Policies allow or block domains and site categories.
Use boat when
your agent browses and also works: installs, builds, Docker and dev servers on a full VM whose disk is saved every minute, with no session cap once auto-stop is off, and coding agents 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 Browserbase, and has to move files between the two.
- Runs as long as the task, keeps its disk. A browsing job that runs past 6 hours on Browserbase has to be split into sessions. Files outside the browser profile come back only if you save them as downloads and fetch them yourself.
- Coding agents you drive from outside, keys kept outside. On Browserbase you either use its Agent as it is or write your own harness around a session, and keys for other APIs are read by your Function code at runtime instead of staying outside it.
Questions people ask
Is boat cheaper than Browserbase?
The table sets a 4 vCPU / 8 GB boat VM against a Browserbase browser session that keeps no disk. 50 agents in parallel come to $317 on boat against $841. 300 sandboxes for your users and 1,000 jobs at once are above Startup's 100 concurrent browsers, so Browserbase needs its Scale plan, which has no public price. boat fits the 300 sandboxes at $200, but its start limits refuse the 1,000-job burst.
Can Browserbase run Docker or a shell?
A Browserbase session gives you Chrome over CDP, not a shell on the VM. Its hosted Agent and Functions can run shell commands in a short TypeScript runtime with no persistent storage. Every boat sandbox has root, SSH, Docker, systemd and /dev/kvm.
How long can a Browserbase session run?
Up to 6 hours on Developer and Startup, 15 minutes on Free, and 6+ hours on Scale. After each session the VM is recreated from scratch. A Context keeps the browser profile, and the Downloads API keeps downloaded files. boat has no session cap once auto-stop is off (paid plans; default 1 hour), and keeps the disk at least 14 days after a stop.
Does boat have residential proxies or CAPTCHA solving like Browserbase?
No. boat runs Chrome on datacenter IPs and has no built-in residential proxies or CAPTCHA solving. For sites that block bots at volume, Browserbase's residential proxies, CAPTCHA solving and Verified browsers are built for that.
Can I use boat and Browserbase together?
Yes. An agent on a boat sandbox can open a Browserbase session over CDP, or call its Fetch and Search APIs, and keep its code, files and tools on the boat VM. That puts protected browsing on Browserbase and the rest of the work on a machine that keeps its disk.
Is boat SOC 2 compliant?
SOC 2 is in progress, and no HIPAA BAA is documented. Live status is at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention. Sandboxes run only in the EU (Germany, Finland and France); snapshot copies can be stored outside the EU. A zero data retention option exists.
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 Browser Use
- Browserbase vs Steel
- Browserbase vs Hyperbrowser
- Browserbase vs Kernel
- Browserbase vs Anchor Browser
- Browserbase vs Browserless
- Browserbase vs Notte
- Browserbase vs Scrapeless