boat vs Islo

Islo and boat both run every sandbox as a VM with its own kernel, with credentials kept outside and coding agents built in. boat adds a desktop for computer use, /dev/kvm for emulators and ports you can host on, and it costs less in every scenario below.

Where boat stands out

A desktop agents can see and use

Every boat sandbox has a 60fps desktop with Chromium, a computer-use API for clicks and keys, and a stream you can embed in your app. Islo sandboxes are headless: they have a browser for tests, but no screen and no computer-use API.

Nested virtualization and systemd

boat gives every machine root, systemd, Docker and /dev/kvm, so an agent can run Android emulators, Firecracker or a VM of its own inside the sandbox. Islo runs Docker inside its microVMs, but its docs do not mention /dev/kvm or nested virtualization.

Ports you can host on

On boat you can serve up to 50 ports over HTTPS with token protection, open raw TCP, and keep the URLs as long as the sandbox lives. Islo shares one HTTP port per link, anyone with the URL can open it, and it expires after a TTL, 24 hours by default.

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
Hardware: Dedicated AMD Ryzen 9 9950X (Zen 5) hosts
Regions: EU: Germany, Finland, France
Plans: From $20 a month, all of it usage credit, 7-day trial

Islo

Islo is an agent sandbox from Incredibuild: each coding agent gets its own microVM, with network rules and credentials handled at a gateway.

An Islo sandbox is a Linux microVM with its own kernel, built from a container image, with Claude Code, Cursor CLI and Codex preinstalled. Outbound traffic can pass through a gateway that allows or blocks hosts, injects credentials and logs every request. It is built for teams that run coding agents, evals and RL rollouts in the background, on Islo's cloud or in their own cloud account.

Maker: Incredibuild, a build acceleration company based in Tel Aviv
Launched: May 4, 2026
Isolation: A microVM with its own kernel for each agent computer
Regions: US West on Islo's cloud; BYOC puts the control plane and sandboxes in your own cloud account
Billing: CPU per core, memory per GB and disk per GB while a sandbox runs, billed per hour; signup credits with no card
Compliance: No certification named on its site; compliance documents on request from support

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	Islo: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Islo runs Docker inside its microVMs, but no /dev/kvm or desktop is documented, so Android emulators and browser testing on a screen need boat.	3rd cheapest of 367 $634 a month	326th of 367, with limits $7,402 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both fit, since both keep a VM running with no session cap; Islo can pause an idle assistant with its memory and wake it on the next request.	5th cheapest of 366 $657 a month	30th cheapest of 366 $9,928 a month
Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Neither is a perfect fit for one-minute bursts: Islo needs a raised concurrency limit, and boat's start limits queue very large bursts.	186th of 345, with limits $2,000 a month	153rd of 345, with limits $503 a month
Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month 300 sandboxes for your users at once is more than the 50 running sandboxes reported for Islo's Team plan, so it needs a custom limit there.	Cheapest of 361 $209 a month	171st of 361, with limits $3,160 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	167th of 360, with limits $15,265 a month
Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month Islo has a built-in Harbor integration with $250 of credit for Harbor users and gateway rules that stop trials from looking up answers; boat runs evals on more sandboxes at once.	10th cheapest of 364 $200 a month	198th of 364, with limits $2,456 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	119th cheapest of 377 $1,507 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	18th cheapest of 368 $26 a month	112th cheapest of 368 $402 a month
Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Islo sandboxes are headless with no screen or computer-use API, while boat streams a 60fps desktop with Chromium that agents can see and click.	6th cheapest of 369 $200 a month	310th of 369, with limits $2,210 a month
Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Islo has a browser for testing inside the sandbox; boat adds a visible desktop and a computer-use API on top of browser control.	7th cheapest of 367 $200 a month	113th of 367, with limits $1,105 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	66th cheapest of 346 $748 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	265th of 338, with limits $14,966 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	47th of 360, with limits $746 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	Islo
Isolation	Every sandbox is a full VM with its own kernel	Every sandbox is a microVM with its own kernel
Docker and nested virtualization	Docker, root, systemd and /dev/kvm on every machine	Docker inside and sudo; no /dev/kvm or nested virtualization documented
Desktop and computer use	60fps desktop and Chromium, computer use and browser control, embeddable stream	A browser inside the sandbox for testing; no desktop or computer-use API
Pause and resume	Snapshots every minute and on stop; a stopped sandbox costs nothing; resume reboots from disk	Pause keeps files, processes and memory; can pause after idle time and resume on the next exec, file access or webhook
Fork	Fork a running sandbox into new ones	Snapshot a running sandbox's files, then start new sandboxes from it
Reaching the sandbox	HTTPS URLs for up to 50 ports, token-protected; raw TCP; its own IP	HTTPS share links that anyone with the URL can open, expiring after a TTL (24 hours by default); SSH and port-forward through the CLI; no raw TCP over shares
Outbound internet rules	Open internet on every plan; no provider-side allowlist	Gateway profiles allow or deny by host, path and HTTP method, with default deny, rate limits and content filters
Keeping keys out of the sandbox	AI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out	Gateway injects stored credentials into outbound requests for any host; credentials never reach the sandbox
Coding agents	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API	Claude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps with events, steer and follow-ups, on a schedule, webhook or GitHub, Slack and Linear events
Request logs	Usage API and spend limits; no per-request log of outbound calls	Per-request gateway logs of what each agent called and what was blocked, streamed to your SIEM
Sandboxes at once	100 to 2,000 running sandboxes by plan, raised by adding seats	Free 5 and Team 50 running sandboxes per launch coverage; paused ones do not count; more by contract
Where it runs	EU only: Germany, Finland, France; EU data residency and zero data retention	US West, or inside your own cloud account with BYOC
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	Islo
Full VM (own kernel)	Yes	Yes
Docker inside	Yes	Yes
Nested virtualization	Yes	No
Root	Yes	Yes
Systemd	Yes	Not published
Desktop GUI	Yes	No
Browser	Yes	Yes
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	Yes
Memory fork	No	No
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	No
Public IPv4	No	No
Egress allowlist	No	Yes
Secret proxy	Yes	Yes
Secret proxy for any API	Yes	Yes
Preinstalled agents	Yes	Yes
Agent harness API	Yes	Yes
MCP server	No	No
GPU	No	No
Windows	No	No
Arm64	No	No
Self-hosting	No	No
BYOC	No	Yes
Open source	No	No
Scoped API keys	Yes	Not published
Spend limits	Yes	Not published
Usage per sandbox (API)	Yes	Yes
Audit logs	No	Yes
SSO	No	Yes
SOC 2	No	Not published
HIPAA	No	Not published
EU data residency	Yes	No
Zero data retention	Yes	Not published

Performance

boat26.69 runs/s

IsloNot measured

There is no comparable measurement: Islo was not part of StarSling's public sandbox benchmark run or the other public results we use. In StarSling's run of 2026-09-29, boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB on dedicated AMD Ryzen 9 9950X (Zen 5) hosts.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Islo 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	Islo, 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	$101 · Free
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$26 · $20/mo	$420 · Free
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	$4,863 · Team
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	$1,382 · Team · 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	$3,053 · Team · with limits

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.

Islo: Islo bills each CPU core and each GB of memory and disk you give a sandbox while it runs, billed per hour, with no plan fee. An idle sandbox keeps billing until a pause-after-idle timer fires, and that timer can only be set when the sandbox is created; egress has no published price.

Limits in those scenarios

Islo's Team plan is reported at 50 running sandboxes at once, and paused ones do not count. That is why 300 sandboxes for your users and 1,000 short jobs at once do not fit Islo without a custom contract. On boat the limit is a sandbox count (100 to 2,000 by plan) plus starts per minute, so the 1,000-job burst gets queued and needs more starts per day than the $2,000 plan allows. Islo publishes no egress price, so every Islo total here leaves egress out.

Scenario	boat	Islo
One coding agent, workdays	None that bite	egress price not published
One agent that never stops	None that bite	egress price not published
50 agents in parallel	None that bite	egress price not published
Sandboxes for your users	None that bite	Team: max 50 concurrent egress price not published
1,000 short jobs at once	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)	Team: max 50 concurrent egress price not published

Which one should you use?

Use Islo when

you need per-host egress rules with a log of every outbound call, sandboxes that pause with memory and wake on request, or a US region or your own cloud account.

Egress rules and request logs. Useful if you must control what agents reach: Islo allows or blocks each host, path and method, and logs every call.
Pause with memory, wake on request. Useful for agents that sit idle between tasks: Islo pauses them with memory kept and resumes on the next request.
US region and your own cloud. Useful if your data must stay in the US or in your own cloud account: Islo runs in US West or under BYOC.

Use boat when

your agents need more than a shell: a desktop for computer use, /dev/kvm for emulators, ports you can host on, and up to 2,000 sandboxes at once on a full VM in the EU.

A desktop agents can see and use. An agent that has to check a UI, fill a form in a real app or show a person what it did needs a screen. On Islo you would install a VNC stack and a control layer yourself in each image.
Nested virtualization and systemd. Mobile app tests, OS work and tools that start their own VMs stop at the first emulator boot without /dev/kvm. Software emulation, where it works at all, runs many times slower.
Ports you can host on. A preview a teammate opens next week, a database a test client dials, or a game server on UDP or TCP needs a stable, private address. On Islo that means re-sharing links or running a CLI tunnel on your own machine.

Questions people ask

Is boat cheaper than Islo?

In every scenario we priced, yes: one coding agent on workdays comes to $20 a month on boat and $101 on Islo, and one agent running all month comes to $26 versus $420. 50 agents in parallel come to $317 versus $4,863. For 1,000 short jobs at once, boat lands at $2,000 and Islo at $3,053, and neither fits without higher limits.

Are Islo sandboxes containers or VMs?

VMs. Islo runs each agent computer in a microVM with its own kernel, built from a container image. boat also gives every sandbox a full VM, and adds systemd and /dev/kvm.

Does Islo have a desktop or computer use?

No. Islo sandboxes are headless Linux machines with a browser for testing, and its docs list no desktop or computer-use API. boat streams a 60fps desktop with Chromium and has a computer-use API on every sandbox.

Can I limit what an agent reaches on the internet?

On Islo, yes: a gateway profile allows or denies traffic by host, path and HTTP method, can block everything by default, and logs each request. boat sandboxes have open internet with no provider-side allowlist, while its credentials proxy keeps real API keys out of the sandbox.

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. Islo runs in US West, or inside your own cloud account with BYOC.

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. Islo names no certification on its site and sends compliance documents on request.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial