boat vs Civo
A Civo Compute instance is a plain Linux VM that you set up and run yourself, billed by the hour even while it is stopped. boat gives an agent a full VM too, with snapshots every minute, free stops, fork, HTTPS ports, a desktop and coding agents already built in.
Where boat stands out
A disk saved every minute, and fork while running
boat saves a sandbox's disk every minute and when it stops, and a stopped sandbox costs nothing. You can fork a running sandbox in one call. A stopped Civo instance is billed the same as a running one, and its snapshot API is documented for CivoStack Enterprise private regions and organizations where it is enabled.
Coding agents and a desktop built in
Every boat sandbox has Claude Code, Codex, OpenCode and other agents ready, and you drive them from outside with a prompt, steer and events API. It also streams a 60fps desktop with Chromium for computer use. The credentials proxy keeps real AI keys out of the machine and can switch to another account when one runs out of credits.
HTTPS on up to 50 ports, no setup
Each boat sandbox can serve up to 50 ports on HTTPS URLs, protected by a token, plus raw TCP. A Civo instance has a public IP and any port you open in its firewall, but HTTPS means running your own proxy and certificates or adding a load balancer.
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
Civo
Civo is a general-purpose cloud, and Civo Compute is its service for Linux virtual machines, called instances.
A Civo instance is a Linux VM you rent by size, with root, NVMe storage, a public IP and free data transfer. Civo runs this compute layer on Kubernetes, next to its managed Kubernetes, load balancers, firewalls, object storage and GPU machines. It is a server host, not an agent sandbox, so this page compares the two where they overlap: giving an agent its own Linux machine.
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 | Civo: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both give a full Linux VM with root and Docker, but a Civo instance starts empty and is billed while stopped, while boat comes with agents, snapshots and free stops. | 3rd cheapest of 367 $634 a month | 112th of 367, with limits $1,048 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB A Civo instance can run an assistant around the clock, but you build the agent setup, the HTTPS endpoint and the backups yourself; boat has them built in. | 5th cheapest of 366 $657 a month | 151st of 366, with limits $1,086 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Neither fits short runs cleanly: Civo bills every started hour in full, so a one-minute job costs an hour, and boat's start limits queue big bursts. | 186th of 345, with limits $2,000 a month | 170th of 345, with limits $1,086 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Civo accounts start at a basic quota that is raised on request after a period of proven use, so hundreds of user sandboxes need a quota review first; boat allows 100 to 2,000 by plan. | Cheapest of 361 $209 a month | 97th of 361, with limits $893 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 | 183rd of 360, with limits $21,726 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 | 48th cheapest of 364 $893 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Both run Docker builds on a full VM; on Civo each job is billed up to a full hour, and you run the runner software and the clean-up between jobs yourself. | 4th cheapest of 377 $86 a month | 111th cheapest of 377 $1,161 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both fit a 24/7 dev box: a Civo instance is a classic always-on server, and a boat machine keeps its disk with snapshots every minute. | 18th cheapest of 368 $26 a month | 35th cheapest of 368 $43 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month boat streams a 60fps desktop with Chromium and computer use; on a Civo instance you install and run a desktop and VNC yourself. | 6th cheapest of 369 $200 a month | 253rd of 369, with limits $1,190 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 7th cheapest of 367 $200 a month | 299th of 367, with limits $893 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 | 173rd of 346, with limits $89 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 | 68th of 338, with limits $1,786 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 | 166th of 360, with limits $149 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month Only Civo fits: it rents Nvidia GPU machines by the hour, and boat has no GPUs. | 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 | Civo |
|---|---|---|
| What you get | A sandbox API for agents, on full VMs | A general Linux VM you set up and run yourself |
| Isolation | Every sandbox is a full VM with its own kernel | Every instance is a VM, run on Civo's Kubernetes-based compute layer |
| CPU | Dedicated AMD Ryzen 9 9950X (Zen 5) hosts; 26.69 runs/s at 4 vCPU / 8 GB | CPU model not published; no comparable measurement |
| Docker and nested virtualization | Docker, root, systemd and /dev/kvm on every machine, documented | Root and Docker; nested virtualization is not documented |
| Stopping | A stopped sandbox costs nothing and keeps its disk | A stopped instance is charged the same as a running one; you delete it to stop paying |
| Snapshots | Automatic snapshots every minute and on stop | Disk snapshots by API or schedule, documented where configured on a CivoStack Enterprise private region |
| Fork | Fork a running sandbox in one call (disk, no memory) | Restore a disk snapshot into a new instance, where snapshots are enabled (disk, no memory) |
| Reaching the machine | HTTPS URLs for up to 50 ports, token-protected; raw TCP; own IP | Public IPv4 on any port; load balancers for HTTP or TCP; TLS certificates are yours to set up |
| Desktop and computer use | 60fps desktop and Chromium, computer use and browser control, embeddable stream | Headless Linux; you install a desktop and VNC yourself |
| Coding agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | None; you install and supervise agents yourself |
| Keeping keys out of the machine | AI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out | No credentials proxy; you put secrets on the instance yourself, for example with an init script |
| Outbound rules and transfer | Open internet on every plan; no provider-side allowlist | Firewalls with allow or deny rules for ingress and egress by port and CIDR; data transfer is free with no limits |
| GPUs | None | Nvidia L40S, A100, H100, H200, B200 and B300 machines |
| Regions | EU only: Germany, Finland, France | London, Frankfurt, New York and Mumbai |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | Not published |
Every feature Battleships tracks (43)
| Feature | boat | Civo |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | Yes |
| Desktop GUI | Yes | No |
| Browser | Yes | No |
| Computer-use API | Yes | No |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | No |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | Yes |
| Public IPv4 | No | Yes |
| Egress allowlist | No | Yes |
| 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 | Yes |
| 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 | Yes |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | Not published |
| HIPAA | No | Not published |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement for Civo Compute: it was not part of the public StarSling benchmark run where boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Civo does not publish which CPU its standard instances run on, so we have no basis for a speed comparison.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Civo 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 | Civo, 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 | $10 · Usage account |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $43 · Usage account |
| 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 | $524 · Usage account |
| 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 | $893 · Usage account |
| 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 | $5,952 · Usage account |
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.
Civo: Each instance size has a fixed hourly price, and every started hour is billed in full, so a one-minute job costs an hour. A stopped instance is billed the same as a running one, so paying only for working hours means deleting the instance and rebuilding it; data transfer is free.
Limits in those scenarios
Civo limits each account with one quota for instances, CPUs, RAM and disk across all regions. New accounts start at a basic level, and Civo raises it on request after a period of proven use, so 50 agents, 300 user sandboxes or 1,000 jobs at once need a quota increase first. Hourly rounding is what makes the short-job scenarios expensive there. On boat the limit is a sandbox count (100 to 2,000 by plan) plus starts per minute, so 1,000 short jobs at once get queued and need more starts per day than the $2,000 plan allows.
| Scenario | boat | Civo |
|---|---|---|
| One coding agent, workdays | None that bite | None that bite |
| One agent that never stops | None that bite | None that bite |
| 50 agents in parallel | None that bite | None that bite |
| Sandboxes for your users | None that bite | None that bite |
| 1,000 short jobs at once |
| None that bite |
Which one should you use?
Use Civo when
you need GPUs, regions in the UK, US or India, or a long-lived server that sits next to managed Kubernetes, load balancers and firewall rules in one cloud.
- GPUs by the hour. Useful if your agents train or serve models: Civo rents Nvidia GPUs from L40S to B300, on demand or committed.
- Regions in the UK, US and India. Useful if your users or data must stay in the UK, the US or India: Civo runs in London, New York and Mumbai as well as Frankfurt.
- Free transfer and network rules. Useful if the agent moves a lot of data or must only reach chosen IP ranges: transfer is free and firewalls filter egress.
Use boat when
you want each agent on its own full VM that is ready to work: coding agents, a desktop, HTTPS ports and minute-by-minute snapshots built in, and stops that cost nothing.
- A disk saved every minute, and fork while running. Agents sit idle for hours between tasks. On Civo you either keep paying for an idle instance or script delete and rebuild yourself, and lose whatever the agent changed since your last backup.
- Coding agents and a desktop built in. A Civo instance starts as an empty server, so you install, update and supervise each agent, desktop and API key yourself, and the keys sit on the machine where the agent's code can read them.
- HTTPS on up to 50 ports, no setup. An agent that starts a dev server wants to share a working link right away. On Civo that link is a bare IP with no TLS and no access token until you set them up for each machine.
Questions people ask
Is boat cheaper than Civo?
It depends on how the machine runs. One coding agent on workdays comes to $10 a month on Civo against $20 on boat, if you delete the Civo instance every evening. One agent that never stops comes to $26 on boat against $43 on Civo, 50 agents in parallel come to $317 against $524, and sandboxes for your users come to $200 against $893. For 1,000 short jobs at once Civo comes to $5,952 a month, and boat needs higher limits than its $2,000 plan.
Do I pay for a Civo instance that is stopped?
Yes. Civo's billing docs say a stopped instance is chargeable exactly like an active one, until you delete it. On boat, a stopped sandbox costs nothing and keeps its disk.
Can I run Docker and nested VMs on Civo?
Docker works, since a Civo instance is a VM with root. Civo does not document nested virtualization or /dev/kvm for its instances. On boat, Docker, systemd and /dev/kvm are documented on every machine.
Does Civo have snapshots and fork?
Civo's API can snapshot an instance's disk and restore it over the original or into a new instance, but the docs describe it where configured on a CivoStack Enterprise private region, and the guide says it must be enabled for your organization. boat snapshots every sandbox every minute and on stop, and can fork a running sandbox in one call.
Where does my data run?
boat runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. Civo has regions in London, Frankfurt, New York and Mumbai.
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