Agent 37 vs Islo

Agent 37 gives each user a light gVisor sandbox that sleeps when idle and keeps its memory, with a full VM type as an extra. Islo gives every coding agent a microVM with its own kernel and an optional gateway that decides what it can reach and logs each call.

The companies and products

Agent 37

Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.

You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor. A VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.

Islo

Islo is an agent sandbox and coding-agent factory 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. Islo also runs factory lines: saved agents run steps on a schedule, on a webhook or on GitHub, Slack, Linear and Jira events. It runs on Islo's cloud or in your own cloud account.

Launched
May 4, 2026

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. “4th cheapest of 365” means 3 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 workloadAgent 37: price rankIslo: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Islo runs Docker in every microVM. Agent 37 needs its VM type for Docker, at 2.5 times the compute rate. boat adds systemd, /dev/kvm and a built-in desktop on every sandbox.
4th cheapest of 365
$551 a month
60th of 365, with limits
$7,402 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
Both can pause an idle assistant with its memory and wake it on the next request. Agent 37 is built for one always-on assistant per user, and in this page's estimate it costs $12 a month to keep one running, against $420 on Islo.
Cheapest of 361
$279 a month
37th cheapest of 361
$9,928 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Agent 37's small default sandboxes suit short code runs. Islo publishes no concurrency limit, and launch coverage reported 50 on Team. boat's $20 plan includes 12 starts a minute and 200 a day, and extra starts cost $0.03 to $0.07.
Cheapest of 336
$22 a month
155th of 336, with limits
$503 a month
189th of 336, with limits
$2,000 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Agent 37 runs up to 1,000 awake instances after $1,000 of top-ups; sleeping ones do not count. Islo publishes no limit, and launch coverage reported 50 running on Team. boat plans go up to 2,000 at once.
Cheapest of 349
$79 a month
172nd of 349, with limits
$3,160 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
9th of 349, with limits
$363 a month
174th of 349, with limits
$15,265 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
Islo has a Harbor integration, its Harbor docs show 300 trials at once, and gateway rules can stop trials from looking up answers. boat also runs Harbor evals, on up to 2,000 sandboxes at once, with no provider-side egress rules.
Cheapest of 359
$58 a month
203rd of 359, with limits
$2,456 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
227th of 374, with limits
$96 a month
124th cheapest of 374
$1,507 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
All three keep a machine and its disk around the clock. Agent 37 costs the least to keep running in this page's estimate, and boat's full VM adds systemd and /dev/kvm.
3rd cheapest of 371
$12 a month
117th cheapest of 371
$402 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Agent 37 adds a noVNC desktop through a template build. On Islo you set it up: a setup script installs Xvfb and a VNC server, and your own tooling drives it. boat streams a 60fps desktop on every sandbox.
3rd cheapest of 367
$120 a month
63rd cheapest of 367
$2,210 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
47th of 356, with limits
$29 a month
151st of 356, with limits
$1,105 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
Cheapest of 343
$32 a month
71st cheapest of 343
$748 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
39th of 327, with limits
$648 a month
266th of 327, with limits
$14,966 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
Agent 37 and boat fork a running machine's disk, and the fork boots fresh. Islo snapshots a running sandbox's files and starts new sandboxes from it. None copies memory.
Cheapest of 351
$43 a month
78th of 351, with limits
$746 a month
3rd cheapest of 351
$200 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 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 requirementNot ranked: misses a requirement

Key features

FeatureAgent 37Isloboat
IsolationgVisor container by default; full VM with its own kernel as an opt-in typeEvery sandbox is a microVM with its own kernelEvery sandbox is a full VM with its own kernel
Docker insideOnly on the VM type, at 2.5x the default compute rateDocker inside every microVM, with sudoDocker, root and systemd in every sandbox
Nested virtualization/dev/kvm on the VM type, with a ready Android templateNo /dev/kvm or nested virtualization documented/dev/kvm in every sandbox, Android emulators work
Sleep with memoryOpt-in auto-sleep after idle time, memory checkpointed, wakes on the next requestPause keeps files, processes and memory; can pause after idle time and resume on the next exec, file access or webhookStop keeps the disk for at least 14 days with no compute charge; memory is not saved, so a resume is like a reboot
Fork and snapshotsFork a running, stopped or sleeping instance (disk copy, the fork boots fresh); nightly backups in 7 slots plus one on-demandSnapshot a running sandbox's files, then start new sandboxes from itFork a running sandbox from its last 1-minute snapshot; disk saved every minute; saved snapshots that new sandboxes start from
Custom imagesYour own linux/amd64 Docker image as a templateSandboxes built from a container imageStart from boat's image or a saved snapshot; you cannot boot your own Docker image
Desktop and computer useYou set it up: noVNC desktop through a template build, or the Ubuntu VM templateBrowser-use capability built in; no desktop or computer-use API. You set it up: install Xvfb and a VNC server with a setup script60fps desktop and Chromium, computer-use API, embeddable stream
Outbound internet rulesOpen internet; no egress allowlistOpen by default; optional gateway profiles allow or deny by host, path and HTTP method, with default deny and rate limitsOpen internet; no provider-side allowlist
Keys kept out of the sandboxManaged models, search and Composio through a per-instance token; your own keys go in as env varsGateway injects stored credentials into outbound requests for any hostOptional paid proxy ($1 a day plus $1 per 1,000 requests) for model providers and HTTPS APIs you register; other secrets still enter the sandbox
Reaching the sandboxHTTPS URL per port, signed URLs, custom domains; no public IP; SSH through a WebSocket tunnelHTTPS share links open to anyone with the URL, expiring after a TTL (24 hours by default); SSH through the CLIUp to 50 HTTPS URLs, token-protected by default; SSH; raw ports over IPv6 only on sandboxes with no IPv4 of their own
Built-in agentsHermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API per instanceClaude Code, Cursor CLI and Codex; factory lines run on a schedule, webhook or GitHub, Slack, Linear and Jira eventsClaude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code, Mistral Vibe, with a prompt, steer and events API
Request logsNo per-request log of outbound calls documentedPer-request gateway logs of what each agent called and what was blocked, streamed to your SIEMUsage API and spend limits; no per-request log of outbound calls
Sandboxes at once3 awake before a top-up, then 10, 50, 200 and 1,000 as top-ups grow; sleeping and stopped ones do not countNo limit on the pricing page; launch coverage (May 2026) reported 5 on Free and 50 on Team; paused ones do not count100 to 2,000 running sandboxes by plan, with included starts per minute, hour and day
Where it runsDedicated servers in the United StatesIslo's cloud (regions not published, set per account), or your own cloud account with BYOCGermany, Finland and France; no region choice, no US or Asia region; snapshot copies can be stored outside the EU
Every feature Battleships tracks (43)
FeatureAgent 37Isloboat
Full VM (own kernel)No documented wayYesYes
Docker insideNo documented wayYesYes
Nested virtualizationNo documented wayNo documented wayYes
RootYesYesYes
SystemdNot publishedNot publishedYes
Desktop GUIWith your own setupWith your own setupYes
BrowserYesYesYes
Computer-use APINo documented wayNo documented wayYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkNo documented wayNo documented wayNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo documented way
Wake on requestYesYesNo documented way
HTTPS preview URLsYesYesYes
Raw TCP inboundNot publishedNo documented wayYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistNo documented wayYesNo documented way
Secret proxyYesYesYes
Secret proxy for any APINo documented wayYesYes
Preinstalled agentsYesYesYes
Agent harness APIYesYesYes
MCP serverNo documented wayNo documented wayNo documented way
GPUNo documented wayNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingNo documented wayNo documented wayNo documented way
BYOCNo documented wayYesNo documented way
Open sourceNo documented wayNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsYesYesYes
Usage per sandbox (API)YesYesYes
Audit logsNot publishedYesNo documented way
SSONo documented wayYesNo documented way
SOC 2YesNot publishedNo documented way
HIPAANo documented wayNot publishedNo documented way
EU data residencyNo documented wayNo documented wayNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

Agent 37Not measured
IsloNot measured
boat28.06 runs/s

Agent 37 and Islo are 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/s 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. Agent 37 says its default instances share host resources and sells a Performance type on dedicated cores.

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. Agent 37 and Islo are 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.

ScenarioAgent 37, a monthIslo, a monthboat, 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
$6 · Wallet (any top-up)$101 · Free$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$12 · Wallet (any top-up)$420 · Free$26 · $20/mo
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$329 · Wallet ($50 lifetime top-ups)$4,863 · Team$317 · $20/mo × 3 seats
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$33 · Wallet ($1,000 lifetime top-ups)$1,382 · Team · with limits$200 · $100/mo × 2 seats
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$73 · Wallet ($1,000 lifetime top-ups) · with limits$3,053 · Team · with limits$8,800 · $2000/mo · with limits

Agent 37: A prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while stopped or asleep. VM compute costs 2.5x and Performance compute 4x the default rate.

Islo: Islo has no plan fee. It bills $0.07 per CPU-hour, $0.04 per GB-hour of memory and $0.0007 per GB-hour of disk while a sandbox runs, with signup credits and no card. A running idle sandbox bills at full rate until a pause-after-idle timer fires, and that timer can only be set at creation. Egress prices are not published.

Islo: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, per second while it runs. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; extra saved snapshots and the AI credentials proxy still charge. A card is required, also for the 7-day trial.

Limits in those scenarios

Agent 37 runs up to 1,000 awake instances after $1,000 of top-ups, so 300 user sandboxes fit it. The 50-agent fleet needs Docker, so it is priced on Agent 37's VM type at 2.5x compute. Islo publishes no concurrency limit; launch coverage reported 50 running on Team, so the table treats 300 user sandboxes and 1,000 jobs at once as needing a higher limit from Islo. Neither publishes an egress price, so their totals leave egress out. boat fits 300 at once, but it limits starts per minute, hour and day, and above 3 times the included rate per minute a start fails with 429, so the 1,000-job burst does not fit boat. Agent 37 runs that burst on shared vCPUs, which the table marks as a compromise.

ScenarioAgent 37Isloboat
One coding agent, workdays
  • egress price not published
  • egress price not published
None for this scenario
One agent that never stops
  • egress price not published
  • egress price not published
None for this scenario
50 agents in parallel
  • egress price not published
  • egress price not published
None for this scenario
Sandboxes for your users
  • egress price not published
  • Team: max 50 concurrent
  • egress price not published
None for this scenario
1,000 short jobs at once
  • shared vCPUs on this tier: heavy, sustained CPU use can be slowed by other tenants
  • egress price not published
  • Team: max 50 concurrent
  • egress price not published
  • 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

Which one should you use?

Use Agent 37 when

you host one mostly idle assistant per customer in the US that should sleep with its memory kept, and you want the lowest bill of the three.

  • Built for one assistant per user. Useful for hosting a mostly idle assistant per customer: it sleeps, keeps its memory and wakes on the next message.
  • Low cost to keep machines around. Agent 37 bills per minute from a prepaid wallet, with no plan fee, and costs less than Islo in every scenario we priced.
  • Your Dockerfile, dedicated cores. Agent 37 builds templates from your own Docker image and sells a Performance type on dedicated cores.

Use Islo when

your coding agents need a microVM with Docker, per-host egress rules with a log of every call, credentials injected for any host, or sandboxes inside 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.
  • A VM with Docker by default. Every Islo sandbox is a microVM with its own kernel and Docker inside, with no separate VM type to pay extra for.
  • Runs in your own cloud. Useful if sandboxes must stay in your own cloud account: Islo can deploy its control plane and sandboxes there with BYOC.

Where boat fits

If your agents do hours of real work, like installs, builds, Docker, emulators and UI checks, look at boat. Every sandbox is a full VM with systemd, /dev/kvm and a 60fps desktop, and plans go up to 2,000 sandboxes at once. boat has no egress rules, no pause with memory and no US region.

Docker, systemd and /dev/kvm on every machine

On Agent 37 Docker needs the VM type at 2.5 times the compute rate, with no init system. Islo runs Docker but documents no /dev/kvm, so Android emulators and tools that start their own VMs have no documented way to run.

A desktop agents can see and use

Islo has a browser-use capability but no built-in screen; you install a VNC stack yourself. Agent 37 needs a noVNC template build. boat streams a 60fps desktop with Chromium and a computer-use API in every sandbox.

Ports you can host on

boat serves up to 50 HTTPS ports, token-protected by default. Islo share links are public and expire after a TTL, 24 hours by default. boat's IP changes at each resume, and raw ports are IPv6 only on sandboxes with no IPv4 of their own.

Use boat when your agents need a full VM with systemd, /dev/kvm and a 60fps desktop, ports you can host on, and up to 2,000 sandboxes at once. Compare it one to one: boat vs Agent 37 and boat vs Islo.

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

Questions people ask

Is Agent 37 cheaper than Islo?

Yes, in every scenario we priced. One coding agent on workdays comes to $6 a month on Agent 37 and $101 on Islo, one agent running all month to $12 versus $420, and 50 agents in parallel to $329 versus $4,863. boat lands at $20, $26 and $317 for the same three. Islo totals leave out egress.

Which is faster, Agent 37 or Islo?

Neither is in the public benchmarks we use, so we cannot say. Agent 37 sells a Performance type on dedicated cores for steady speed. boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB in StarSling's run of 3 October 2026, on an AMD Ryzen 9 9950X host.

Can Agent 37 and Islo run Docker?

Islo runs Docker inside every microVM. Agent 37 runs Docker only on its VM type, which bills compute at 2.5x; the default gVisor type cannot run a Docker daemon. boat runs Docker in every sandbox.

Are they containers or VMs?

An Agent 37 sandbox is a gVisor container by default, with a full VM as an opt-in type. Every Islo sandbox is a microVM with its own kernel. Every boat sandbox is a full VM with systemd and /dev/kvm.

Can an idle agent sleep and keep its memory?

Yes on both. Agent 37 checkpoints memory on auto-sleep and wakes on the next request. Islo pauses with files, processes and memory and resumes on the next exec, file access or webhook. boat keeps the disk of a stopped sandbox for at least 14 days with no compute charge, but a resume is like a reboot.

Where do Agent 37 and Islo run?

Agent 37 runs on dedicated servers in the United States. Islo runs on its own cloud, with regions set per account and not published, or inside your own cloud account with BYOC. boat runs on machines in Germany, Finland and France; snapshot copies can be stored outside the EU.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons