boat vs shellbox
Both give you a real Linux VM with root, Docker and nested virtualization, hosted in Finland. shellbox is a lean SSH box that pauses with its memory when you log off, while boat is built to run many agents at once, with the agents, a desktop and key handling already inside.
Where boat stands out
Agents and keys built in
Claude Code, Codex and other agents come preinstalled, and you prompt, steer and follow them from outside through one API. Real API keys stay outside the sandbox in a credentials proxy, and a credential can switch to another account when one runs out of credits.
Fleets, not a handful of boxes
boat plans start at 100 sandboxes at once and go to 2,000, and you can fork a sandbox while it runs. shellbox allows 16 running slots per account, so 8 boxes of 4 vCPU, and copies a box only once it is stopped.
A screen and real hosting
Every boat sandbox has a 60fps Linux desktop and Chromium for computer-use and browser agents. It also serves HTTPS on up to 50 ports, token-protected by default, plus raw TCP and its own IP.
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
shellbox
shellbox sells instant Linux boxes over SSH for builders and AI agents, with no signup: your SSH key is your account.
Each box is a microVM on Firecracker by default, or Cloud Hypervisor when you need /dev/kvm, running Ubuntu 24.04 with Docker on Hetzner servers in Helsinki. You manage everything with SSH commands that can return JSON, and a box pauses with its memory when you disconnect and resumes when you connect again. It is built for developers who want a cheap dev box they use a few hours a day, and for agents that already speak SSH.
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 | shellbox: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory runs many agents at once, and shellbox's 16 running slots allow only 8 boxes of 4 vCPU, while boat plans start at 100 sandboxes at once. | 3rd cheapest of 367 $634 a month | 63rd of 367, with limits $485 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both can keep a box running all month; boat adds preinstalled agents you drive from outside and keeps real API keys out of the machine. | 5th cheapest of 366 $657 a month | 111th of 366, with limits $628 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month shellbox fits short bursts well because a box pauses with its memory and comes back in seconds, and it bills per minute with no plan fee. | 186th of 345, with limits $2,000 a month | 65th of 345, with limits $67 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month shellbox's account caps stop well short of hundreds of user sandboxes, and its terms forbid reselling or sublicensing access to the service. | Cheapest of 361 $209 a month | 37th of 361, with limits $211 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month shellbox can copy a stopped box with its memory snapshot, so rollouts can branch from the same running state. | 34th of 360, with limits $2,000 a month | 17th of 360, with limits $1,000 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 | 95th of 364, with limits $160 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 | 143rd of 377, with limits $96 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB This is shellbox's home ground: a box that pauses when you log off, keeps its processes, and works with VS Code Remote, Zed and mosh. | 18th cheapest of 368 $26 a month | 17th cheapest of 368 $25 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Computer-use agents need a screen, and boat ships a 60fps Linux desktop with Chromium while shellbox is SSH only. | 6th cheapest of 369 $200 a month | 88th of 369, with limits $147 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month boat has Chromium and a desktop in every sandbox; on shellbox you install and run a headless browser yourself. | 7th cheapest of 367 $200 a month | 158th of 367, with limits $80 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 6th cheapest of 346 $90 a month | 180th of 346, with limits $98 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 71st of 338, with limits $1,800 a month | 75th of 338, with limits $1,950 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 | 112th of 360, with limits $49 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 | shellbox |
|---|---|---|
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Firecracker microVM by default, or Cloud Hypervisor; own kernel and disk per box |
| Biggest machine | Up to 16 vCPU / 32 GB on the $100 plan and above | Up to 16 vCPU / 32 GB (x8); size is fixed at creation |
| Machines at once | 100 on the $20 plan, up to 2,000 on the $2,000 plan, more per paid seat | 16 running slots per account, so 8 boxes of 4 vCPU; no published way to raise it |
| Pause and resume | Disk is saved every minute and on stop; resume boots the machine again | Pauses with a memory snapshot; reconnect in about 3 seconds with processes and shell history intact |
| Stopping when idle | Stops when the time to live you set runs out; no idle timer | Pauses 120 seconds after the last SSH session ends; wakeup mode stops after idle |
| Wake on request | No; a stopped sandbox is started by API | Yes; wakeup mode starts a box on an HTTPS request, and cron mode wakes it on a schedule |
| Fork | Fork a running sandbox with its disk | Duplicate a stopped box with its disk and memory snapshot; live duplicate is an open feature request |
| Nested virtualization | Yes, /dev/kvm for Android emulators and VMs | Yes on Cloud Hypervisor boxes (--ch); not on the default Firecracker backend |
| Docker and root | Root, systemd and Docker in every sandbox | Root and Docker on stock Ubuntu boxes; boxes made from OCI images do not include Docker |
| Inbound access | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 | One public HTTPS URL to port 80, custom domains, and a stable public IPv6 for raw TCP and UDP; no IPv4 |
| Desktop and browser | 60fps Linux desktop and Chromium with computer use | None; access is SSH, SFTP and port forwarding |
| Coding agents | Claude Code, Codex and others preinstalled, with a prompt, steer and events API | You install your agent, start it in tmux over SSH and tell it to stop the box when done |
| Keeping API keys out of the sandbox | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out | No secret store; docs suggest SSH agent forwarding, pasting a token, or adding an SSH key inside the box |
| Regions | EU only (Germany, Finland, France) | EU only (Helsinki, Finland); US region planned |
| 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 | shellbox |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | Yes |
| Root | Yes | Yes |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | No |
| Computer-use API | Yes | No |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | Yes |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | No |
| 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 | Yes |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | Yes |
| Public IPv4 | No | No |
| Egress allowlist | No | No |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | No |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | No |
| 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 | No |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | No |
| HIPAA | No | No |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement for shellbox. boat did 26.69 runs per second on the StarSling hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts, but shellbox has not been run on the same test, so we make no speed claim either way.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. shellbox 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 | shellbox, 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 | $6 · Prepaid |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $26 · Prepaid |
| 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 | $317 · Prepaid · 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 | $90 · Prepaid · 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 | $200 · Prepaid · 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.
shellbox: shellbox is prepaid with no plan fee: a running box costs $0.02 an hour per x1 slot, billed per minute, and a paused box costs $0.50 a month per slot. Boxes stop when the balance drops below $5 and are deleted at $0.
Limits in those scenarios
shellbox allows 16 running slots per account, and a 4 vCPU box uses two, so only 8 such boxes run at once. That is why the 50-agent fleet and the 300 user sandboxes do not fit, and its site names no way to raise the cap. Neither fits 1,000 jobs at once: boat's $2,000 plan allows 2,400 starts a day and queues bursts above 90 a minute. shellbox also says bandwidth is shared and may be throttled, and its terms bar resource-intensive background processes.
| Scenario | boat | shellbox |
|---|---|---|
| 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 shellbox when
you want one or a few personal SSH boxes that pause with their memory when you log off, or small services that should wake only on a request.
- Pauses with its memory. Useful for dev boxes you come back to: processes, shell history and TCP state are restored in about three seconds.
- Wakes on a request or a schedule. Good for small web services and periodic jobs that should only run, and bill, while there is work.
- Plain SSH, no account. Fits people who live in a terminal: your SSH key is the account, and VS Code Remote, Zed and mosh just work.
Use boat when
you run many agents at once and want them preinstalled and driven from outside, with a desktop and browser, keys kept out of the machine, and hosting on many ports.
- Agents and keys built in. On shellbox you start the agent in tmux over SSH, and its docs suggest pasting tokens or adding an SSH key that can control your whole account inside the box, where a prompt injection can reach them.
- Fleets, not a handful of boxes. Fifty parallel agents or a few hundred user sandboxes do not fit in shellbox's 16 slots, and it publishes no way to raise them; branching an agent there means stopping it first.
- A screen and real hosting. shellbox is SSH only and routes HTTPS to port 80 alone, so a browser agent runs headless with nothing to watch, and an app with an API, a frontend and a preview needs a proxy you set up yourself.
Questions people ask
Is boat cheaper than shellbox?
Not for one agent on workdays: shellbox costs about $6 a month against boat's $20 plan. Running all month, both come to about $26. For 50 agents both cost about $317 a month, but shellbox's 16-slot cap does not fit that fleet.
How many boxes can I run at once on shellbox?
Up to 16 running slots and 64 total slots per account, where a box uses as many slots as its size. That is 16 boxes of 2 vCPU, or 8 of 4 vCPU. boat starts at 100 sandboxes at once on the $20 plan.
Can I run Claude Code on shellbox?
Yes. You install it in the box, start it in a tmux session over SSH, and can tell it to stop the box when it is done. On boat, Claude Code and other agents are preinstalled and you prompt and steer them through an API.
Does shellbox have an API?
Yes, over SSH: every command can return stable JSON, and your SSH key authenticates each call. There is no REST endpoint or SDK. boat has a REST API and a CLI.
Do both support Docker and nested virtualization?
Yes. shellbox stock boxes ship with Docker, and boxes created with --ch on Cloud Hypervisor expose /dev/kvm. boat has Docker and /dev/kvm in every sandbox.
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