boat vs Morph Cloud

Both give each agent a full Linux VM with root and Docker. Morph Cloud is strongest at snapshotting and branching a running machine with its memory, and at waking a paused machine on the next request. boat comes with coding agents, a desktop with Chrome and an optional key proxy already inside, and it has the lower monthly bill in four of the five scenarios on this page.

Where boat stands out

Coding agents you drive from outside

Claude Code, Codex and five other agents come preinstalled in every boat sandbox. You send a prompt, steer the agent and follow its events through one API. On Morph you install the agent yourself and run it inside tmux, sending keystrokes and reading the screen.

Real keys can stay outside the machine

With boat's optional credentials proxy on, the real keys of supported model providers and of custom HTTPS APIs you register, such as Stripe, stay outside the sandbox. The proxy costs $1 a day plus $1 per 1,000 requests. Environment variables, the GitHub token and other secrets still enter the sandbox. A credential can also switch to another account when one runs out of credits. Morph documents no key proxy; its examples put API keys inside the VM.

A desktop and a browser, ready to use

Every boat sandbox has a Linux desktop streamed at 1920x1080 and 60fps, with Chrome and computer tools for agents, and you can embed it in your app. Graphics run on the CPU, because boat has no GPU. Morph offers browser-based remote access. Its docs have you install the browser and wire up any computer use agent yourself.

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.

Morph Cloud

Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.

You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state. It also sells managed GitHub Actions runners and a shared filesystem.

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 rankMorph Cloud: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Both run Docker and full builds. boat adds preinstalled coding agents you prompt and steer by API. On Morph you set it up: install the agent and drive it through the tmux API.
5th cheapest of 365
$634 a month
215th of 365, with limits
$2,288 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month gets agents, a desktop and an optional paid credentials proxy on boat, with auto-stop turned off. On Morph you set these up yourself, and a paused VM wakes on the next request.
6th cheapest of 361
$657 a month
272nd of 361, with limits
$3,014 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Morph fits short code runs well: a machine can pause with its memory, bill only its snapshot storage while paused, and wake on the next request.
189th of 336, with limits
$2,000 a month
20th cheapest of 336
$154 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Both fit. Morph can pause each user's machine and wake it on the next request. boat gives each user up to 50 token-protected HTTPS URLs and raw ports on a public IPv6 address.
3rd cheapest of 349
$209 a month
21st cheapest of 349
$905 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Morph's memory branching suits rollouts that all start from the same running state.
39th of 349, with limits
$2,000 a month
92nd of 349, with limits
$4,847 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
51st cheapest of 359
$675 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Morph also sells managed GitHub Actions runners. On boat you set it up: run your own runner inside a sandbox, with nested virtualization available.
2nd cheapest of 374
$86 a month
37th cheapest of 374
$355 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
19th cheapest of 371
$26 a month
86th cheapest of 371
$116 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
boat ships a 1920x1080, 60fps desktop with Chrome and computer tools for agents. On Morph you set it up: install the browser and a computer use agent on its remote desktop.
7th cheapest of 367
$200 a month
219th of 367, with limits
$595 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
boat has Chrome ready on its desktop. On Morph you set it up: its docs run headless Chrome in Docker and expose its debug port.
7th cheapest of 356
$200 a month
267th of 356, with limits
$250 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
286th of 343, with limits
$234 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
152nd of 327, with limits
$4,750 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
245th of 351, with limits
$228 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

FeatureboatMorph Cloud
IsolationFull VM with its own kernel on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are sharedFull VM with its own kernel
Root, Docker and systemdYesYes, including Docker in Docker and local Kubernetes
Nested virtualizationYes, /dev/kvm on every sandbox for Android emulators and VMsExperimental
Pause with memoryNo; the disk is saved, and a resume is like a rebootYes; resume brings back all processes and memory, and a paused VM bills only its snapshot
Fork a running machineYes, with its disk as of the last save (at most a minute old), without memoryYes, with its memory, as many copies as you ask for, in under 250 ms
Wake on requestNo; a stopped sandbox is started by APIYes; a paused VM resumes on the next HTTP request, SSH or exec call
Saving work automaticallyDisk saved every minute and on every stop; a stopped sandbox costs no machine time and keeps its disk for at least 14 daysSaved when you pause or snapshot; a TTL can pause the VM automatically with its memory; a plain stop releases the instance
Desktop and browser1920x1080, 60fps Linux desktop with Chrome and computer tools for agentsBrowser-based remote desktop; you set up the browser and any computer use agent (its docs run headless Chrome in Docker)
Coding agentsSeven agents preinstalled, with a prompt, steer and events APIYou set it up: install the agent, then drive it through a tmux API that sends keys and reads the screen
Keeping API keys out of the sandboxOptional paid proxy ($1 a day plus $1 per 1,000 requests) for model providers and custom HTTPS APIs; other secrets still enter the sandboxNo documented proxy that keeps model or API keys outside the VM; keys are set inside the machine (Morph's scoped agent tokens cover only its own API)
Inbound accessUp to 50 HTTPS URLs, token-protected by default; raw ports on a public IPv6 addressNamed HTTP services with optional API key auth; SSH and SSH port forwarding through Morph's gateway; no public raw TCP
Guest systemsLinux; Windows programs run through Wine on the desktop, no Windows VMLinux, with experimental Windows and macOS (x86)
Where machines runGermany, Finland and France; no region choice and no US or Asia region; snapshot copies can be stored outside the EURegions not published
Managed CI runnersNo managed runner; you set it up: run your own runner inside a sandboxGitHub Actions runners in three sizes, billed from the same MCU balance
Compliance and transparencySOC 2 is in progress. We're open about where we stand: live status and data retention policy.Not published
Every feature Battleships tracks (43)
FeatureboatMorph Cloud
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesYes
RootYesYes
SystemdYesYes
Desktop GUIYesYes
BrowserYesNo documented way
Computer-use APIYesNo documented way
SSHYesYes
Persistent diskYesYes
Pause/resumeYesYes
Automatic snapshotsYesYes
Fork/cloneYesYes
Live fork (no pause)YesYes
Memory forkNo documented wayYes
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNo documented wayYes
Wake on requestNo documented wayYes
HTTPS preview URLsYesYes
Raw TCP inboundYesNo documented way
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 APIYesYes
MCP serverNo documented wayNo documented way
GPUNo documented wayNo documented way
WindowsNo documented wayYes
Arm64No documented wayNo documented way
Self-hostingNo documented wayNo documented way
BYOCNo documented wayNo documented way
Open sourceNo documented wayNo documented way
Scoped API keysYesYes
Spend limitsYesNot published
Usage per sandbox (API)YesYes
Audit logsNo documented wayYes
SSONo documented wayNot published
SOC 2No documented wayNot published
HIPAANo documented wayNot published
EU data residencyNo documented wayNot published
Zero data retentionYesNot published

Performance

boat28.06 runs/s
Morph CloudNot measured

Morph 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), boat did 28.06 runs per second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. 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. Morph says it restores a snapshot in under 250 ms, which measures start time, not CPU speed.

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. Morph 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 monthMorph 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 · Developer
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$121 · Team
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$1,459 · Scale
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$325 · Scale
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$869 · Scale

boat: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. Included time does not carry over. You pay per second while a sandbox runs: $0.036 an hour for 4 vCPU / 8 GB, busy or idle. The $20 plan includes 12 starts a minute, 60 an hour and 200 a day. An extra start costs $0.03 to $0.07, and a start above 6 times the included number (3 times per minute) fails. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Saved snapshots above the included 10 ($0.056 each a day) and the credentials proxy ($1 a day plus $1 per 1,000 requests) still charge while sandboxes are stopped.

Morph Cloud: Morph bills MCUs at $0.05 each: per hour, a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps, for its configured size. The Free plan costs $0 and includes no MCUs: you buy MCUs to use compute. Team ($40 a month for 1,000 MCUs) and Scale ($250 a month for 7,500 MCUs) are prepaid bundles at a discount. A paused VM bills only its snapshot storage.

Limits in those scenarios

Morph prices each machine by its largest resource, so more than 16 GiB of disk per vCPU raises the bill, and egress prices are not published. Morph's always-on figure assumes the VM stays awake; one that pauses when idle (a TTL pause plus wake on request) costs less. Morph's Free plan allows up to 64 vCPU and 8 Devboxes at once; Team allows 32 Devboxes and Scale 128. boat's $20 plan allows 100 sandboxes at once and includes 200 starts a day. At 1,000 short jobs at once, boat's $2,000 plan charges for starts above 90 a minute and refuses them above 270, while Morph Scale fits. boat auto-stop defaults to 1 hour; you can set up to 30 days or turn it off on a paid plan. A boat resume is like a reboot: memory and running programs are not saved, and the IP address changes. If a boat machine fails, you lose what was written after the last 1-minute snapshot. boat has no GPU, no Windows VM and no region choice, and you cannot boot your own Docker image.

ScenarioboatMorph Cloud
One coding agent, workdaysNone for this scenario
  • disk beyond 16 GiB: price unknown
  • egress price not published
One agent that never stopsNone for this scenario
  • disk beyond 16 GiB: price unknown
  • egress price not published
50 agents in parallelNone for this scenario
  • disk beyond 16 GiB: price unknown
  • egress price not published
Sandboxes for your usersNone for this scenario
  • 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
  • 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 Morph Cloud when

your agents branch from one running state with its memory, sleep between requests and wake on demand, or need experimental Windows and macOS guests.

  • Memory snapshots, branching and wake on request. Useful for agents that fan out from one running state or sleep between requests: a paused VM keeps its memory and wakes on demand.
  • Windows and macOS guests. Morph lists experimental Windows and macOS (x86) guests for agents that must work in those systems.
  • Managed CI runners and a shared filesystem. Morph also sells managed GitHub Actions runners and a filesystem many machines can mount at once.

Use boat when

your agents need to arrive ready: coding agents you prompt and steer by API, a desktop with Chrome for computer use, an optional proxy that keeps real model and API keys outside the machine, and HTTPS on many ports, at a lower monthly bill in four of our five scenarios.

  • Coding agents you drive from outside. Driving an agent by keystrokes means parsing terminal output to know when it is done or stuck. You build and maintain that harness, and it can break when the agent's screen layout changes.
  • Real keys can stay outside the machine. On Morph, API keys sit inside a machine the agent controls, where one prompt injection can leak them. To avoid that, you build and run your own proxy outside the VM.
  • A desktop and a browser, ready to use. A browsing or computer use agent on Morph starts with you building the desktop image, the browser and the screenshot and click loop before the agent can do any work.

Questions people ask

Is boat cheaper than Morph Cloud?

In four of the five scenarios on this page, yes. One 4 vCPU / 8 GB agent that runs all month costs $26 on boat and $121 on Morph. For 1,000 short jobs at once, Morph's Scale plan fits, while boat's plans charge for starts above 90 a minute and refuse them above 270. Morph's price drops if you let the VM pause when idle, and a boat sandbox bills at full rate while it runs, busy or idle.

Can boat branch a running VM with its memory like Morph?

No. boat forks a running sandbox from its last 1-minute disk snapshot, without memory, so the copy boots fresh and can miss the last minute of writes. Morph's Infinibranch copies the memory too, so every branch continues with its processes running.

Do both run Docker and nested virtualization?

Both are full VMs with root and Docker inside. boat exposes /dev/kvm on every sandbox for Android emulators and VMs. Morph lists nested virtualization as experimental.

Can I run Claude Code or Codex on each?

Yes. On boat they come preinstalled, and you prompt, steer and follow them through an API. On Morph you set it up: install them in a Devbox and drive them through a tmux API that sends keystrokes and captures the screen.

Does Morph Cloud have computer use?

Morph has browser-based remote desktop access. You set up the browser and the computer use agent yourself; its docs run headless Chrome in Docker and expose its debug port. boat ships a 60fps desktop with Chrome and computer tools in every sandbox.

Is boat SOC 2 compliant?

SOC 2 is in progress. No HIPAA BAA and no SAML SSO are documented. boat measures 99.95% sandbox uptime over the history of all sandboxes, and publishes no SLA. Live status is at status.ascii.dev and our data retention policy is at docs.boat.dev/data-retention.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial

More comparisons