Runloop vs Islo

Both give each coding agent its own VM. Runloop adds a desktop for computer use, arm64 and Dockerfile builds, while Islo adds a gateway that checks and logs every outbound request and pauses idle sandboxes with their memory kept.

The companies and products

Runloop

Runloop is a US platform of sandboxes, called devboxes, for building, running and testing AI coding agents.

You get Linux devboxes built from Dockerfile-style blueprints, disk snapshots, HTTPS tunnels, agent gateways that hide API keys, and Axons, event streams that drive agents such as Claude Code. Each devbox runs in a micro-VM on Runloop's own bare-metal hypervisor, with a container layer inside. It is built for teams shipping coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.

Compliance
SOC 2 Type 2

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.

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. “20th cheapest of 367” means 19 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 workloadRunloop: price rankIslo: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Runloop fits fully, while Islo is a compromise with no desktop or /dev/kvm documented; boat adds /dev/kvm for Android emulators on top of a desktop.
20th cheapest of 367
$8,152 a month
326th of 367, with limits
$7,402 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
All three fit: Islo pauses an idle assistant with its memory on any plan, Runloop needs the Pro plan to suspend, and boat keeps the disk across free stops.
32nd cheapest of 366
$10,194 a month
30th cheapest of 366
$9,928 a month
5th cheapest of 366
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
44th cheapest of 345
$525 a month
153rd of 345, with limits
$503 a month
186th of 345, 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
300 sandboxes for your users at once is more than the 50 running sandboxes reported for Islo's Team plan, while Runloop publishes no cap and boat fits on its plans.
26th cheapest of 361
$3,301 a month
171st of 361, with limits
$3,160 a month
Cheapest of 361
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Runloop ranks 4th for RL rollouts because it starts large waves without published start limits; Islo's 50-sandbox Team limit makes it a compromise.
4th cheapest of 360
$15,922 a month
167th of 360, with limits
$15,265 a month
34th of 360, 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 and gateway rules that stop trials from looking up answers, but its Team limit caps how many run at once; boat ranks higher than both.
81st cheapest of 364
$2,562 a month
198th of 364, with limits
$2,456 a month
10th cheapest of 364
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Runloop and Islo are close here and both run Docker inside; boat's faster CPUs finish builds and test runs sooner.
121st cheapest of 377
$1,554 a month
119th cheapest of 377
$1,507 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
113th cheapest of 368
$410 a month
112th cheapest of 368
$402 a month
18th cheapest of 368
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Runloop ships a desktop and browser an agent can control, while Islo sandboxes are headless; boat streams its desktop at 60fps and you can embed it in your app.
39th cheapest of 369
$2,306 a month
310th of 369, with limits
$2,210 a month
6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
40th cheapest of 367
$1,153 a month
113th of 367, with limits
$1,105 a month
7th cheapest of 367
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
68th cheapest of 346
$781 a month
66th cheapest of 346
$748 a month
6th cheapest of 346
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
266th of 338, with limits
$15,611 a month
265th of 338, with limits
$14,966 a month
71st of 338, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
Both can lock a sandbox to listed hosts; Islo goes further with path and method rules and a log of each call, and boat adds a full kernel with nested virtualization.
10th cheapest of 360
$770 a month
47th of 360, with limits
$746 a month
2nd cheapest of 360
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Can't run itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureRunloopIsloboat
IsolationMicro-VM on a custom bare-metal hypervisor, plus a container layerEvery sandbox is a microVM with its own kernelFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker and nested virtualizationDocker on the dnd blueprints, as root; no nested virtualization documentedDocker inside and sudo; no /dev/kvm or nested virtualization documentedDocker, root, systemd and /dev/kvm on every machine
Desktop and computer useDesktop and browser an agent can controlA browser inside the sandbox for testing; no desktop or computer-use API60fps desktop and Chromium, computer use and browser control, embeddable stream
Images and CPU architectureBlueprints built from Dockerfiles; x86_64 and arm64Built from a container image; x86_64Templates from named snapshots, no Dockerfile builds; x86_64 only
Idle pause and wakeSuspend after idle, wake on an HTTP request to the tunnel (Pro plan)Pause keeps files, processes and memory; resume on the next exec, file access or webhook, on any planNo idle timer; disk snapshot every minute and on stop, a stopped sandbox costs nothing, resume reboots from disk
Keeping filesDisk kept through suspend (Pro plan) or manual disk snapshots; shutdown ends the devboxKept through pause; snapshots of a running sandbox's filesSnapshot every minute and on stop, on every plan; resume with the same disk
Long runsFixed lifetime 1 hour by default, 48 hours max; an idle policy replaces itNo published cap; runs until you stop itNo session cap on paid plans; default TTL 1 hour, changeable
Reaching the sandboxOne HTTPS tunnel per devbox, open or bearer token; SSH through a TLS proxy; no public IPHTTPS share links anyone with the URL can open, 24-hour TTL by default; SSH and port-forward through the CLIHTTPS URLs for up to 50 ports, token-protected; raw TCP; its own IP
Outbound internet rulesHostname allowlist with wildcards, or block allGateway rules by host, path and HTTP method, default deny, rate limits and content filtersOpen internet on every plan; no provider-side allowlist
Request logsNot documentedPer-request gateway logs of each call and each block, streamed to your SIEMUsage API and spend limits; no per-request log of outbound calls
Keeping keys out of the sandboxAgent gateways for any API endpoint with bearer, header or basic authGateway injects stored credentials into outbound requests for any hostAI credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Coding agentsClaude Code, Codex, OpenCode, Gemini CLI, DeepAgents, driven through Axons and BrokerClaude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps on a schedule, webhook or GitHub, Slack and Linear eventsClaude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Sandboxes at onceNo cap published for Basic or Pro; 3 on the trialFree 5 and Team 50 running sandboxes per launch coverage; more by contract100 to 2,000 running sandboxes by plan, raised by adding seats
Where it runsRegions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise)US West, or inside your own cloud account with BYOCEU only: Germany, Finland, France; EU data residency
Every feature Battleships tracks (43)
FeatureRunloopIsloboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoNoYes
RootYesYesYes
SystemdNot publishedNot publishedYes
Desktop GUIYesNoYes
BrowserYesYesYes
Computer-use APIYesNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkNoNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APIYesYesYes
MCP serverYesNoNo
GPUNoNoNo
WindowsNoNoNo
Arm64YesNoNo
Self-hostingNoNoNo
BYOCYesYesNo
Open sourceNoNoNo
Scoped API keysYesNot publishedYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)NoYesYes
Audit logsNot publishedYesNo
SSOYesYesNo
SOC 2YesNot publishedNo
HIPAANot publishedNot publishedNo
EU data residencyNoNoYes
Zero data retentionNot publishedNot publishedYes

Performance

Runloop8.29 runs/s
IsloNot measured
boat26.69 runs/s

On StarSling's Node.js build-and-test benchmark at 4 vCPU / 8 GB (run 36498291449, 2026-09-29), Runloop scored 8.29 runs a second and boat 26.69, about 3.2 times faster. Islo was not part of that run or the other public results we use, so there is no comparable score for it. The test measures CPU work only, not start time or network speed.

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.

ScenarioRunloop, 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
$113 · Basic$101 · Free$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$429 · Basic$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
$5,268 · Basic$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
$1,441 · Basic$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
$3,184 · Basic$3,053 · Team · with limits$2,000 · $2000/mo · with limits

Runloop: Runloop bills per second for the CPU and memory you allocate, including start, suspend and resume, and bills disk for the devbox's whole life. Basic has no plan fee; Pro adds $250 a month that is not usage credit and unlocks suspend.

Islo: Islo bills each CPU core and GB of memory and disk while a sandbox runs, billed per hour, with no plan fee. An idle sandbox keeps billing until a pause-after-idle timer fires, and that timer is set only at creation.

Islo: Plans start at $20 a month and the whole fee is usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Islo's Team plan is reported at 50 running sandboxes at once, so 300 sandboxes for your users and 1,000 short jobs at once do not fit without a custom contract; Runloop publishes no cap there and fits both. Runloop's lifetime setting tops out at 48 hours unless an idle policy replaces it, and suspend needs Pro. Neither publishes an egress price, so their totals leave egress out. boat fits every scenario except the 1,000-job burst, where its start limits queue the jobs.

ScenarioRunloopIsloboat
One coding agent, workdays
  • egress price not published
  • egress price not published
None that bite
One agent that never stops
  • egress price not published
  • egress price not published
None that bite
50 agents in parallel
  • egress price not published
  • egress price not published
None that bite
Sandboxes for your users
  • egress price not published
  • Team: max 50 concurrent
  • egress price not published
None that bite
1,000 short jobs at once
  • egress price not published
  • Team: max 50 concurrent
  • egress price not published
  • 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)

Which one should you use?

Use Runloop when

your agents need a desktop to click, arm64 or Dockerfile builds, very large waves of short jobs, or devboxes inside your own AWS, GCP or Azure account.

  • A desktop for computer use. Useful if your agent must see and click a screen: Runloop ships a desktop and browser it can control, while Islo is headless.
  • arm64 and Dockerfile builds. Useful for arm64 builds and teams with Dockerfiles: Runloop builds blueprints from Dockerfiles and offers arm64 machines.
  • Large waves of sandboxes. Useful for RL rollouts and big bursts: Runloop publishes no concurrency cap on paid plans, while Islo's Team plan is reported at 50.

Use Islo when

you need rules and a log for every outbound request, sandboxes that pause with memory and wake on request without a plan fee, or a US region or your own cloud.

  • Rules and logs for every request. Useful if you must control what agents reach: Islo allows or blocks each host, path and method, and logs every call.
  • Pause with memory on any plan. Useful for agents that sit idle: Islo pauses with memory kept and wakes on the next request, with no plan fee.
  • Sessions with no lifetime setting. Useful for long unattended jobs: an Islo sandbox runs until you stop it, with no keep-alive timer to replace.

Where boat fits

Runloop and Islo both put agents in microVMs and focus on control: tunnels, gateways and egress rules. If your agents do heavy work for hours, such as builds, tests, Docker, emulators or servers others connect to, boat gives each one a full VM on faster CPUs with ports you can host on. Pick Runloop or Islo instead if a provider-side egress allowlist or a US region is a must.

Nested virtualization

Neither Runloop nor Islo documents /dev/kvm, so an Android emulator or a VM inside the sandbox does not start. boat exposes /dev/kvm with root and systemd on every machine.

Ports you can host on

Runloop reaches devboxes through one HTTPS tunnel and Islo through share links that expire after 24 hours by default, and neither offers raw TCP. boat serves up to 50 HTTPS ports, raw TCP and its own IP.

Faster CPUs, files kept for free

boat ran 26.69 build-and-test runs a second to Runloop's 8.29, and Islo has no public score. Keeping a disk on Runloop needs the $250 Pro plan or your own snapshot code; boat saves it every minute and stops cost nothing.

Use boat when your agents do real work for hours: builds, tests, Docker and emulators on faster CPUs, with a 60fps desktop, ports you can host on and files kept on every plan. Compare it one to one: boat vs Runloop and boat vs Islo.

Questions people ask

Is Runloop cheaper than Islo?

Islo comes out a little lower in our scenarios: one coding agent on workdays is $101 a month on Islo and $113 on Runloop, and 50 agents in parallel are $4,863 versus $5,268. boat comes to $20 and $317 for the same work. Islo's 50-sandbox Team limit means it does not fit 300 user sandboxes at once.

Which is faster, Runloop or Islo?

We cannot say: Runloop scored 8.29 runs a second on StarSling's Node.js benchmark at 4 vCPU / 8 GB, and Islo has no public score. boat scored 26.69 on the same test.

Can Runloop and Islo run Docker?

Yes. Runloop runs Docker on its Docker-in-Docker blueprints, and Islo runs Docker inside its microVMs. Neither documents /dev/kvm, so Android emulators and VMs need boat, which exposes it.

Does Runloop or Islo have a desktop for computer use?

Runloop ships a desktop and browser an agent can control. Islo sandboxes are headless, with a browser for testing and no computer-use API. boat streams a 60fps desktop with Chromium that you can embed in your app.

Can I limit what an agent reaches on the internet?

On both. Runloop allows listed hostnames with wildcards or blocks all traffic, and Islo checks host, path and HTTP method and logs every request. boat has open internet with no provider-side allowlist, and its credentials proxy keeps real API keys out of the sandbox.

Where do Runloop and Islo run?

Runloop does not document its regions, and its Enterprise plan deploys into your own AWS, GCP or Azure account. Islo runs in US West or in your own cloud account with BYOC. boat runs only in the EU, in Germany, Finland and France.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons