Browser Use vs Notte
Browser Use and Notte both rent stealth cloud browsers with proxies and CAPTCHA solving for AI agents. Browser Use bills per browser-hour and scales to 1,000 browsers as lifetime payments grow. Notte sells monthly plans with extra tools such as personas, vaults and browser Functions.
The companies and products
Browser Use
Browser Use makes the popular open-source browser-agent library and runs Browser Use Cloud, a service of managed browsers and a hosted agent that uses them.
Browser Use Cloud is a different kind of product from boat. You get a hardened Chromium browser in their cloud that you drive over CDP with Playwright or Puppeteer, or a hosted agent that you send tasks to through an API. Each hosted agent runs in its own micro-VM, where it can write and run Python and shell commands in a 1 GiB workspace. Stealth fingerprints, CAPTCHA solving and residential proxies are included, and you pay per browser-hour. It is built for teams that need many browsers that get past anti-bot checks, not for a machine that you control with your own shell.
Notte
Notte is a cloud browser platform for AI agents: you start hosted Chrome sessions through an API, SDK, CLI or MCP server.
Each Notte session is a hosted browser you control over CDP, Playwright or Notte's own actions, with residential proxies, captcha solving and a consistent fingerprint on by default. Around it Notte sells the Anything API, which turns a plain-English task into a deployed browser Function. It also sells vaults for credentials, personas with their own email and phone number, and Python Functions that turn a browser script into an API endpoint. Coding agents such as Claude Code and Cursor use Notte through a browser skill, a CLI or an MCP server. Notte is a browser service, not a general sandbox, so this page compares the two where they overlap: agents that use the web.
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 356” means 2 of the other 355 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 | Browser Use: price rank | Notte: price rank | boat: 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 that stays. Browser Use's hosted agent runs its own scripts in a 1 GiB micro-VM, and Notte runs Python Functions. boat has root, Docker and the browser on one VM; Notte documents a boat integration. | 86th of 365, with limits $301 a month | 82nd of 365, with limits $121 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant outlives both sessions: Browser Use agent browsers stop after 4 hours and Notte Startup sessions after 300 minutes. Notte's scheduled Functions can run recurring web tasks. A boat sandbox stops after 1 hour by default; turn auto-stop off on a paid plan. | 104th of 361, with limits $750 a month | 166th of 361, with limits $365 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 213th of 336, with limits $71 a month | 217th of 336, with limits $100 a month | 189th of 336, with limits $2,000 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month | 195th of 349, with limits $270 a month | 192nd of 349, with limits $105 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 223rd of 349, with limits $1,010 a month | 220th of 349, with limits $500 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 229th of 359, with limits $90 a month | 230th of 359, with limits $100 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 220th of 374, with limits $64 a month | 231st of 374, with limits $100 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 227th of 371, with limits $25 a month | 268th of 371, with limits $100 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Both control a browser. Computer-use agents that need other apps fit boat's 60 fps Linux desktop. | 130th of 367, with limits $133 a month | 126th of 367, with limits $100 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both are built for this, with stealth and proxies on by default. In our default ranking for this case, Notte is #2, Browser Use #3 and boat #6. boat fits when the agent also needs a shell and files. | 3rd cheapest of 356 $140 a month | 2nd cheapest of 356 $100 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month At startup scale all three fit. In our default ranking, boat is #6 and Notte #8. boat gives each bot a whole machine with a browser and a disk that is saved between runs. | 17th cheapest of 343 $198 a month | 8th cheapest of 343 $100 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month In our default ranking for mass scraping of sites that block bots, Browser Use is #1 and Notte #2. Browser Use's lifetime-payment tiers reach 1,000 browsers at once, and Notte's Startup plan stops at 100. | Cheapest of 327 $2,950 a month | 2nd of 327, with limits $975 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month Red-team agents need their own tools and a shell. boat gives each one a full VM with root and nftables. | 88th of 351, with limits $68 a month | 190th of 351, with limits $100 a month | 3rd cheapest of 351 $200 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 | 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 | Not ranked: misses a requirement |
Key features
| Feature | Browser Use | Notte | boat |
|---|---|---|---|
| What you get | A hardened Chromium browser over CDP, or a hosted agent in its own micro-VM | A hosted browser session over CDP, Playwright or Notte actions, plus agents, vaults, personas and Functions; isolation model not published | A full Linux VM with its own kernel and root, with Chrome and a desktop on it |
| Browsers at once | 10 with no payment, 50 after $100 paid in total, up to 1,000 after $25,000 | 5, 25 or 100 by plan; custom on Enterprise | 100 to 2,000 sandboxes at once by plan; 12 to 90 starts a minute included, extra starts $0.03 to $0.07, starts above 3 times that fail |
| How long a session runs | Agent browsers stop after 4 hours at most; idle ones stop after about 2 minutes unless you set keepAlive (up to 4 hours) | 15 min on Free, 120 min on Developer, 300 min on Startup; custom on Enterprise, up to the API limit of 24 h | Auto-stop after 1 hour by default; up to 30 days, or off on a paid plan; a running sandbox bills busy or idle |
| What survives a session | Browser profiles keep cookies and logins; the agent workspace keeps up to 1 GiB of files | Fresh browser each session; an opt-in profile keeps cookies, local storage and session storage; session files (up to 10 GiB) stay with that session | The disk, saved every minute and at each stop, kept at least 14 days; memory is not saved; fork a running sandbox |
| Getting past bot checks | Hardened Chromium fork, per-session fingerprints, CAPTCHA solving (off in the EU) | Captcha solving for reCAPTCHA, hCaptcha and Turnstile, and a consistent Chrome fingerprint, on every plan | Chromium on datacenter IPs; you set up your own proxy or captcha service |
| Proxies | Residential proxies in 195+ countries, on by default at $5 per GB, or your own at $0.20 per GB direct | Residential proxies on by default at $10 per GB; your own proxy on Startup ($0.20 per GB) | None managed; you can run your own proxy client inside the VM |
| Hosted agent | Hosted browser agent with a choice of models, a session queue and an events API | Anything API turns a plain-English task into a deployed browser Function; a browser skill, CLI and MCP server for coding agents | Seven coding agents inside the VM, such as Claude Code and Codex, driven from outside with a prompt, steer and events API |
| Logins and identities | Secrets typed into the page by alias, kept out of the task text | Vaults for passwords, cards and 2FA secrets filled through placeholders, and personas with their own email and phone | Your agent logs in itself; the optional paid AI credentials proxy keeps real keys of supported AI providers outside |
| Running your own code | No shell for you; the hosted agent writes and runs Python and shell commands in its own micro-VM | Python Functions with a run() entry point, called by API, webhook or schedule; shell access not documented | Root shell, any language, Docker, systemd and /dev/kvm |
| Desktop | Live view of the browser, embeddable, plus a recording | Live view of the browser that you can embed | A full Linux desktop and Chrome streamed at 60 fps, embeddable and recordable |
| Serving your own ports | Not part of the product: it runs browsers and agents, not your own servers | Not part of the product; a short-lived signed live-view URL per session | Up to 50 HTTPS URLs per sandbox, token-gated by default; raw ports over public IPv6 |
| Source code and self-hosting | The browser-use agent library is MIT and runs on your own machine | Framework under SSPL-1.0 runs on local Chromium; on-premise and bring-your-own-cloud on Enterprise | Hosted service only |
| Regions | US, plus an EU deployment in Frankfurt with fewer features | Session region not published; built-in proxies exit in the US unless you pick a country | Germany, Finland and France; you cannot pick a region; no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Browser Use | Notte | boat |
|---|---|---|---|
| Full VM (own kernel) | Not published | No documented way | Yes |
| Docker inside | No documented way | No documented way | Yes |
| Nested virtualization | No documented way | No documented way | Yes |
| Root | Not published | Not published | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No documented way | No documented way | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | No documented way | No documented way | Yes |
| Persistent disk | Yes | No documented way | Yes |
| Pause/resume | No documented way | No documented way | Yes |
| Automatic snapshots | No documented way | No documented way | Yes |
| Fork/clone | No documented way | No documented way | Yes |
| Live fork (no pause) | No documented way | No documented way | Yes |
| Memory fork | No documented way | No documented way | No documented way |
| Custom image (Docker or snapshot) | Not published | Not published | Yes |
| ≥24 h sessions | No documented way | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | No documented way | No documented way | No documented way |
| HTTPS preview URLs | No documented way | No documented way | Yes |
| Raw TCP inbound | Not published | Not published | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | No documented way | No documented way | Yes |
| Secret proxy for any API | No documented way | No documented way | Yes |
| Preinstalled agents | No documented way | No documented way | Yes |
| Agent harness API | No documented way | No documented way | Yes |
| MCP server | Yes | Yes | No documented way |
| GPU | No documented way | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | Not published | No documented way |
| Self-hosting | Yes | Yes | No documented way |
| BYOC | No documented way | Yes | No documented way |
| Open source | Yes | Yes | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No documented way | No documented way | Yes |
| Audit logs | Not published | Not published | No documented way |
| SSO | No documented way | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Yes | Yes | No documented way |
| EU data residency | Yes | Not published | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Browser Use nor Notte is in the public benchmarks we use, so we cannot say which is faster. Neither publishes the CPU or memory behind a browser session. For browsing work, speed depends mostly on the sites, the proxy and the model. For reference, boat did 28.06 runs per second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15 in StarSling's run of 3 October 2026 (run 37073680030). Every boat sandbox in that 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.
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. Browser Use and Notte are 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 | Browser Use, a month | Notte, a month | boat, 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 | $7 · Pay as you go · with limits | $100 · Startup · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $25 · Pay as you go · with limits | $100 · Startup · with limits | $26 · $20/mo |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $178 · Spend tier 50 · with limits | $100 · Startup · with limits | $317 · $20/mo × 3 seats |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $150 · Spend tier 500 · with limits | $100 · Startup · with limits | $200 · $100/mo × 2 seats |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $210 · Spend tier 1000 · with limits | $100 · Startup · with limits | $8,800 · $2000/mo · with limits |
Browser Use: Browser Use has no subscription. It bills $0.02 per browser-hour, rounded up to whole minutes, from prepaid credits that never expire. Traffic is extra: $5 per GB through the residential proxy, which is on by default, or $0.20 per GB direct. Agent runs add model tokens at listed per-model prices, or your own provider's cost plus 20% with your own key.
Notte: Notte has a Free plan with $10 of one-time credit. Paid plans ($20 Developer, $100 Startup) come back as monthly credits that expire each cycle; top-ups do not expire. Credits pay for browser sessions ($0.01 an hour), Functions ($0.05 an hour), residential proxies ($10 per GB, on by default) and model tokens at cost.
Notte: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. Unused time expires at the end of the period. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge, and boat keeps its disk at least 14 days. Saved snapshots above the included count and the optional AI credentials proxy still charge while sandboxes are stopped. A card is required, also for the 7-day trial.
Limits in those scenarios
Neither fits any scenario in the table as written. Each asks for a general machine, and both sell a browser session of a size they do not publish. Browser Use stops agent browsers after 4 hours and Notte Startup sessions after 300 minutes, which rules out the workday and always-on agents. For many at once, Browser Use needs lifetime payments ($100 for 50 browsers, $25,000 for 1,000), and Notte Startup stops at 100, with anything above on Enterprise. boat fits every scenario except 1,000 short jobs at once. Its $2,000 plan includes 90 starts a minute, charges $0.03 to $0.07 for each extra start and refuses starts above 270 a minute. boat never queues a start.
| Scenario | Browser Use | Notte | boat |
|---|---|---|---|
| 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 |
|
|
|
Which one should you use?
Use Browser Use when
you need many browsers at once on sites with strong bot checks, want to pay per browser-hour with no plan, or want an MIT agent that you can also run yourself.
- Scales to 1,000 browsers. For big scraping jobs: concurrency grows from 10 to 1,000 browsers as lifetime payments grow, with no monthly plan.
- MIT library you can run anywhere. For teams that want the same agent locally: the browser-use library is MIT, with about 120k GitHub stars.
- No plan, credits that keep. For uneven workloads: no monthly plan, and prepaid credits never expire. An EU deployment runs in Frankfurt.
Use Notte when
your agents sign up and log in to sites, so personas, vaults and scheduled browser Functions save you work, or when you need it on your own cloud.
- Identities and vaults built in. For sign-up and login flows: personas with their own email and phone, and vaults that fill passwords and 2FA codes.
- Browser scripts as endpoints. For recurring browser jobs: Functions turn a script into an API you call, hit as a webhook or run on a schedule.
- A flat plan and your own cloud. A $100 Startup plan covers 100 browsers at once, and Enterprise offers on-premise and bring-your-own-cloud.
Where boat fits
Browser Use and Notte are browser services, not general sandboxes, so they overlap with boat where agents use the web. If your agents browse and also write code, keep files, run for hours or use a desktop, look at boat. You can still call Browser Use or Notte from inside a boat sandbox for the pages that fight bots.
A whole machine around the browser
Browser Use's hosted agent runs scripts in a small micro-VM, and Notte runs Python Functions. A boat sandbox is a full VM with root, Docker, systemd and /dev/kvm, with Chrome on it.
Long runs on one disk
Browser Use agent browsers stop after 4 hours and Notte Startup sessions after 300 minutes; profiles carry cookies and storage. boat runs until its auto-stop (1 hour by default, up to 30 days or off on a paid plan), saves the disk every minute and can fork a running sandbox.
A desktop and coding agents
Both stream a browser view, and their agents browse rather than write code. boat streams a 60 fps Linux desktop and ships Claude Code, Codex and other agents that you drive from outside.
Use boat when the agent does more than browse: it writes and runs code, keeps files between runs, works for hours, or needs a desktop, Docker and coding agents on one VM. Compare it one to one: boat vs Browser Use and boat vs Notte.
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
Questions people ask
Is Browser Use cheaper than Notte?
It depends on volume. A workday agent comes to $7 a month on Browser Use against $100 on Notte's Startup plan. For 50 agents in parallel, Notte's flat $100 costs less than Browser Use's $178; boat is $317 for a full VM each. For browser-use agents we model $140 a month on Browser Use, $100 on Notte and $200 on boat. Proxy traffic is billed on top on both browser services.
Which is faster, Browser Use or Notte?
We cannot say. Neither publishes the machine size behind a browser, and neither is in the public benchmarks we use. For browsing work, speed depends mostly on the sites, the proxy and the model.
Which one runs longer sessions?
Browser Use agent browsers run up to 4 hours. Notte sessions run 15 minutes on Free, 120 on Developer and 300 on Startup, with custom limits on Enterprise. A boat sandbox stops after 1 hour by default; on a paid plan you can set up to 30 days or turn auto-stop off.
Can Browser Use or Notte run Docker?
Not as documented. Browser Use's hosted agent runs its own Python and shell commands in a micro-VM, and Notte runs Python Functions; neither documents Docker. boat gives each agent a full Linux VM with Docker, systemd and root.
Are Browser Use and Notte open source?
The browser-use library is MIT and runs on your own machine. Notte's agent framework is on GitHub under SSPL-1.0, which is source-available; its hosted cloud is not, and on-premise is Enterprise only. boat is a hosted service only.
Can I use Browser Use or Notte from a boat sandbox?
Yes. A boat sandbox has open internet, so code or an agent inside it can call either service's API, SDK or MCP server. The agent builds and tests on boat and sends hard-to-reach pages to the stealth browser.
Try boat
Install the CLI, then run boat new.
7-day free trial