boat vs Clever Cloud

Clever Cloud is a platform for hosting apps. You push code or a Docker image, and it runs on immutable VMs that a deploy or a scaling operation replaces. boat gives each agent its own VM with root, Docker, /dev/kvm, a disk that boat saves every minute and coding agents installed.

Where boat stands out

A machine the agent can change

On boat the agent has root via sudo, systemd, Docker with Compose and /dev/kvm, so it can install packages, start services and run emulators. On a Clever Cloud app instance, SSH opens as the non-root user bas, and one container runs per instance unless you open the Docker socket.

Files that stay, and forks

boat saves a sandbox's disk every minute and at each stop. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; a saved snapshot keeps it longer. You can fork a running sandbox from its last 1-minute snapshot to try two paths at once. A Clever Cloud app instance loses disk changes when it is replaced, unless the agent wrote them to an add-on or a CKE volume.

Agents, desktop and keys built in

boat installs seven coding-agent harnesses, including Claude Code, Codex and OpenCode, which you drive from outside with a prompt, steer and events API. Every VM also has a 60 fps desktop with Chrome. The optional, paid credentials proxy keeps real model API keys out of the machine.

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.

Clever Cloud

Clever Cloud is a European platform as a service (PaaS) based in Nantes, France. It hosts web apps, workers and databases for development teams.

You deploy code in one of many runtimes, or a Docker image. Clever Cloud runs it on instances called scalers, each in its own virtual machine, with autoscaling, managed add-ons and HTTPS routing. Instances are immutable: the disk is writable, but changes are lost when a deploy or a scaling operation replaces the instance. Data that must last goes into an add-on (a database, an FS Bucket or Cellar object storage). For several containers or persistent volumes, Clever Cloud points to Clever Kubernetes Engine, in public beta since 27 April 2026. It is a different kind of product from an agent sandbox, so this page compares the parts where the two overlap.

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 workloadboat: price rankClever Cloud: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Clever Cloud is a compromise here. An app instance loses the agent's installs and edits when a deploy or scaling replaces it, and SSH opens as the non-root user bas. To keep files, you set it up: an add-on, or a Ceph volume on Clever Kubernetes Engine (public beta). boat gives root via sudo and saves the disk every minute.
5th cheapest of 365
$634 a month
254th of 365, with limits
$3,233 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that runs for weeks needs files that last. On Clever Cloud you set it up: files go in a database or storage add-on, or a CKE persistent volume. boat saves the VM's disk every minute and keeps a stopped sandbox's disk for at least 14 days; a saved snapshot keeps it longer.
6th cheapest of 361
$657 a month
281st of 361, with limits
$3,352 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Clever Tasks fit short jobs well: Clever Cloud starts a VM, runs the command, stops the VM and bills by the second, with no plan fee. In this scenario Clever Cloud comes to $129 a month and boat to $2,000.
189th of 336, with limits
$2,000 a month
94th of 336, with limits
$129 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
On Clever Cloud you set it up: each user sandbox is a separate app built from a deploy, or a Kubernetes workload on CKE. App instances have no fork or snapshot, and an app has at most 40 instances. boat creates and forks VMs by API; each plan caps starts ($100 plan: 30 a minute, 210 an hour, 840 a day).
3rd cheapest of 349
$209 a month
244th of 349, with limits
$1,068 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
89th of 349, with limits
$4,592 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
151st of 359, with limits
$918 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Both bill by the second. boat CI jobs get root, /dev/kvm and a disk that keeps its cache, and the plan caps starts. A Clever Task starts from the build each time.
2nd cheapest of 374
$86 a month
161st of 374, with limits
$441 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
19th cheapest of 371
$26 a month
136th of 371, with limits
$134 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Clever Cloud has no desktop or browser built in; you set it up: package a browser or a virtual display in your own Docker image (no official example). boat streams a 1920x1080 desktop with Chrome at 60 fps on every VM.
7th cheapest of 367
$200 a month
261st of 367, with limits
$918 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
On Clever Cloud you set it up: package your own browser in a Docker image. boat ships Chrome and browser control on every VM.
7th cheapest of 356
$200 a month
293rd of 356, with limits
$459 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
6th cheapest of 343
$90 a month
276th of 343, with limits
$193 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
73rd of 327, with limits
$1,800 a month
131st of 327, with limits
$3,867 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
246th of 351, with limits
$230 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not ranked: misses a requirementNot 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 requirementNot ranked: misses a requirement

Key features

FeatureboatClever Cloud
Kind of productAgent sandbox: a VM per agent, created and controlled by APIApp hosting platform: deploy code or a Docker image, scale it, add managed databases
IsolationEvery sandbox is a full VM with its own kernel, on a host dedicated to boatEvery app instance runs in its own VM; Docker containers run inside it
Root and system accessRoot via sudo, real systemd and /dev/kvm on every sandboxSSH opens as the non-root user bas; the disk is writable, but changes are lost when a deploy or scaling replaces the instance; no nested virtualization documented
Docker insideDocker with BuildKit and Compose on the sandbox's own kernel; you cannot boot your own Docker image as the machineYour image runs as one container per instance; the Docker socket is opt-in (CC_MOUNT_DOCKER_SOCKET) and Docker Compose is not supported. For several containers, you set it up on Clever Kubernetes Engine (public beta)
Files after a restartDisk saved every minute and at each stop; a stopped sandbox has no compute charge and keeps its disk for at least 14 days. If a machine fails, writes after the last good snapshot are lostAn app instance loses disk changes when a deploy or scaling replaces it. You set it up: a database, Cellar or FS Bucket add-on (FS Buckets are not available to Docker apps), or a Ceph persistent volume on Clever Kubernetes Engine (public beta)
Fork and snapshotsFork a running sandbox from its last 1-minute snapshot; saved snapshots as templatesNo snapshot or fork for app instances; new instances start from a build. Add-ons have their own backups
Reaching the machineUp to 50 HTTPS URLs per sandbox, token-gated by default; public IPv6 address; SSH over IPv4 through a shared host:port; no dedicated IPv4, and the IP changes at each resumeHTTPS on port 8080 with custom domains; one TCP redirection per namespace, on a public port that Clever Cloud chooses and keeps while the redirection exists
Run-to-completion jobsStart a VM, run the job, stop it; each plan caps starts ($20: 12 a minute, 60 an hour, 200 a day), and extra starts cost $0.03 to $0.07Clever Tasks start a VM, run one command and stop the VM, billed by the second, with no plan fee
Managed databases and add-onsNone; you run databases yourself inside the VMManaged databases, object storage, FS Buckets and more, linked to apps by environment variables
Desktop and computer use1920x1080 desktop with Chrome at 60 fps, computer tools for agents, embeddable stream; graphics run on the CPUNot built in; you set it up: package a browser or virtual desktop in your own Docker image (no official example)
Coding agentsSeven harnesses installed, including Claude Code, Codex and OpenCode, with a prompt, steer and events APINot built in; you install an agent in your own image. An MCP server and CLI let agents manage the platform from outside
Keeping keys out of the machineOptional AI credentials proxy ($1 per day on, plus $1 per 1,000 requests): with it on, real keys of supported model providers stay out of the sandbox; other secrets still enter as environment variablesCredentials are injected as environment variables into the instance
RegionsGermany, Finland and France; no US or Asia region; you cannot pick a region, and snapshot copies can be stored outside the EUParis, Roubaix, Gravelines, London, Warsaw, Montreal, Singapore and Sydney; you pick the zone
Certifications and uptimeSOC 2 in progress; 99.95% measured sandbox uptime; no SLA publishedISO 27001:2022 and HDS; Premium plan adds a 99.99% SLA
On your own serversNoClever Cloud On Premises, on request
Compliance and transparencySOC 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)
FeatureboatClever Cloud
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesNo documented way
RootYesNot published
SystemdYesNot published
Desktop GUIYesNo documented way
BrowserYesNo documented way
Computer-use APIYesNo documented way
SSHYesYes
Persistent diskYesWith your own setup
Pause/resumeYesYes
Automatic snapshotsYesNo documented way
Fork/cloneYesNo documented way
Live fork (no pause)YesNo documented way
Memory forkNo documented wayNo documented way
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNo documented wayNo documented way
Wake on requestNo documented wayNo documented way
HTTPS preview URLsYesYes
Raw TCP inboundYesYes
Public IPv4No documented wayNo documented way
Egress allowlistNo documented wayNo documented way
Secret proxyYesNo documented way
Secret proxy for any APIYesNo documented way
Preinstalled agentsYesNo documented way
Agent harness APIYesNo documented way
MCP serverNo documented wayYes
GPUNo documented wayNo documented way
WindowsNo documented wayNo documented way
Arm64No documented wayNo documented way
Self-hostingNo documented wayYes
BYOCNo documented wayNo documented way
Open sourceNo documented wayNo documented way
Scoped API keysYesNot published
Spend limitsYesNot published
Usage per sandbox (API)YesNo documented way
Audit logsNo documented wayNot published
SSONo documented wayNo documented way
SOC 2No documented wayNo documented way
HIPAANo documented wayNo documented way
EU data residencyNo documented wayYes
Zero data retentionYesNot published

Performance

boat28.06 runs/s
Clever CloudNot measured

Clever Cloud is not in the public benchmarks we use, so we cannot say which is faster. In StarSling's run of 3 October 2026 (run 37073680030), a 4 vCPU / 8 GB boat sandbox did 28.06 runs/s on the V8 Web Tooling Benchmark, second of 15. That sandbox ran on an AMD Ryzen 9 9950X host; boat also places sandboxes on Ryzen 7 9700X hosts and does not promise a CPU model. Clever Cloud notes that its nano and pico instances run with reduced CPU priority.

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. Clever Cloud 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.

Scenarioboat, a monthClever Cloud, 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$32 · Pay as you go · with limits
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$134 · Pay as you go · 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$1,616 · Pay as you go · 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$459 · Pay as you go · 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$918 · Pay as you go · with limits

boat: Plans cost $20, $100, $500 or $2,000 a month. The whole plan price comes back as VM time for that month and does not carry over. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second while it runs. Each plan caps starts ($20: 12 a minute, 60 an hour, 200 a day); extra starts cost $0.03 to $0.07 each. A stopped sandbox has no compute charge and keeps its disk for at least 14 days. Saved snapshots above the included count ($0.056 a day each) and the AI credentials proxy still charge while sandboxes are stopped. A card is required, also for the 7-day free trial.

Clever Cloud: Clever Cloud bills each instance by the second of running, at a fixed price per size from pico to 3XL, with no plan fee. This page uses the USD list price for Paris: L (6 vCPU / 8 GiB) at $0.1837 an hour and M (4 vCPU / 4 GiB) at $0.0918 an hour. No size is exactly 4 vCPU / 8 GiB, so the 8 GB scenarios use L and the 4 GB scenarios use M. Disk and egress prices per instance are not published. Premium adds a 490 euro monthly licence, consumption at 1.8 times, a 12-month commitment, a 99.99% SLA and a fixed outbound IP.

Limits in those scenarios

No Clever Cloud scenario fully fits, mainly because it is an app platform. An app instance loses disk changes when it is replaced. CKE volumes can keep files, but each sandbox then becomes a Kubernetes workload you build yourself. Clever Cloud allows up to 40 instances per application and unlimited applications; it publishes no organisation-wide cap on running instances, so 300 or 1,000 at once needs several apps. On boat the 1,000-job burst does not fit as priced either. The $2,000 plan includes 90 starts a minute, 600 an hour and 2,400 a day. Starts above that cost extra ($8,800 a month in this scenario), starts above 270 a minute fail with 429, and boat never queues a start.

ScenarioboatClever Cloud
One coding agent, workdaysNone for this scenario
  • different kind of product: app platform
  • disk beyond 0 GiB: price unknown
  • egress price not published
One agent that never stopsNone for this scenario
  • different kind of product: app platform
  • disk beyond 0 GiB: price unknown
  • egress price not published
50 agents in parallelNone for this scenario
  • different kind of product: app platform
  • disk beyond 0 GiB: price unknown
  • egress price not published
  • how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
Sandboxes for your usersNone for this scenario
  • different kind of product: app platform
  • not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)
  • disk beyond 0 GiB: price unknown
  • egress price not published
1,000 short jobs at once
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429
  • different kind of product: app platform
  • not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)
  • disk beyond 0 GiB: price unknown
  • egress price not published
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 Clever Cloud when

you need to host a finished web app in production with managed databases and autoscaling, need regions outside the EU or managed Kubernetes, or must run the platform on your own servers.

  • Hosting the app your agent built. Useful once the app is done: Clever Cloud runs it in production with autoscaling, managed databases and custom domains.
  • Regions outside the EU and your own servers. Useful if you serve users in Canada, Singapore or Australia, or must run the platform in your own data center.
  • Short jobs with no plan fee. Useful for bursts of short scripts: Clever Tasks start a VM, run one command, stop, and bill by the second.
  • Kubernetes with persistent volumes. Useful if your team already runs on Kubernetes and wants several containers and volumes on EU-run VMs.

Use boat when

agents need a machine to work in: root, Docker, a disk saved every minute, forks, a desktop and coding agents you drive from outside, within the start limits of your plan.

  • A machine the agent can change. Coding agents install tools, edit system files and start services as they go. On a Clever Cloud app instance, a deploy or scaling discards those changes, so lasting ones must go into the image and a new deploy.
  • Files that stay, and forks. On Clever Cloud you set up persistence yourself: a database, object storage or a Kubernetes volume, which an agent's tools do not write to by default. On boat, writes after the last good snapshot are lost if a machine fails.
  • Agents, desktop and keys built in. Clever Cloud says its AI tooling is not an AI-specific product, and it injects secrets as environment variables. On Clever Cloud you build the agent runner, the browser and the key handling yourself.

Questions people ask

Can I use Clever Cloud as a sandbox for AI agents?

Partly. You can deploy a Docker image and SSH in as the non-root user bas. The disk is writable, but changes are lost when a deploy or scaling replaces the instance. To keep files, you set up an add-on or a persistent volume on Clever Kubernetes Engine (public beta). Clever Cloud is built to host apps, so an agent that installs things and keeps files fits a sandbox like boat with less setup.

Is boat cheaper than Clever Cloud?

In four of the five scenarios we priced, yes, at list prices. One coding agent on workdays costs $20 a month on boat and $32 on Clever Cloud (L size). One agent all month costs $26 against $134. 50 agents in parallel cost $317 against $1,616. Sandboxes for your users cost $200 against $459 (M size). For 1,000 short jobs at once, Clever Cloud comes to $918 and boat to $8,800 because of paid extra starts; neither fits as priced. Clever Cloud figures exclude disk and egress, which it does not publish.

Do Clever Cloud apps run in VMs or containers?

In VMs. Clever Cloud runs each application instance in its own virtual machine, and a Docker image runs as a container inside that VM. boat also gives every sandbox its own VM, with root via sudo and a disk saved every minute.

Where does the data live?

boat runs sandboxes on machines in Germany, Finland and France. You cannot pick a region, and snapshot copies can be stored outside the EU. Clever Cloud lets you pick a zone when you create an app: France, London and Warsaw in Europe, or Montreal, Singapore and Sydney.

Is boat SOC 2 compliant?

SOC 2 is in progress; there is no SOC 2 report today. boat publishes no SLA; measured sandbox uptime is 99.95% over the history of all sandboxes. Live status is at status.ascii.dev. Clever Cloud lists ISO 27001 and HDS on its security page.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial

More comparisons