Islo vs Modal VM Sandboxes

Islo and Modal VM Sandboxes both give each agent a VM with its own kernel and Docker inside. Islo keeps a sandbox running with no session cap and guards its traffic at a gateway, while Modal's VMs are short-lived machines that end within 24 hours and scale to thousands at once.

The companies and products

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

Modal VM Sandboxes

Modal is a serverless cloud for AI work, and VM Sandboxes are the version of its sandboxes that run in a virtual machine with their own Linux kernel.

You create a VM Sandbox from Python, TypeScript or Go code with runtime="vm", run commands in it, and terminate it when the job is done. Modal built the runtime on the Rust-based Cloud Hypervisor, so Docker, FUSE, systemd and nested cgroups work, with the same API, images and prices as its gVisor sandboxes. It became generally available on 1 October 2026 and suits teams that want many short-lived agent machines next to Modal's inference and training.

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. “30th cheapest of 366” means 29 of the other 365 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 workloadIslo: price rankModal VM Sandboxes: price rankbochka: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Both run Docker in a VM, but a Modal VM ends within 24 hours and loses files outside a Volume, Islo has no /dev/kvm or desktop documented, and bochka has both plus a disk that stays.
326th of 367, with limits
$7,402 a month
84th of 367, with limits
$759 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
Islo fits an assistant that lives on its machine all month, since it has no session cap and can pause with memory; Modal VM Sandboxes stop at 24 hours.
30th cheapest of 366
$9,928 a month
Can't run it5th cheapest of 366
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Short code runs suit Modal's model of fast starts and thousands of sandboxes at once on Team, while Islo's Team plan is reported at 50 running sandboxes.
153rd of 345, with limits
$503 a month
Can't run it186th 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 user sandboxes at once is more than the 50 running sandboxes reported for Islo's Team plan, and fits Modal's Team plan; bochka also fits and keeps each user's disk while it waits.
171st of 361, with limits
$3,160 a month
Can't run itCheapest of 361
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Huge bursts of short rollouts are what Modal is built for; Islo needs a raised limit for many at once, and bochka's start limits queue very large bursts.
167th of 360, with limits
$15,265 a month
171st of 360, with limits
$16,322 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
198th of 364, with limits
$2,456 a month
Can't run it10th cheapest of 364
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
All three run Docker builds in a VM; Modal offers /dev/kvm for Android emulators only on Team and Enterprise on request, Islo documents none, and bochka has it on every plan.
119th cheapest of 377
$1,507 a month
188th of 377, with limits
$1,064 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
112th cheapest of 368
$402 a month
Can't run it18th cheapest of 368
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Neither Islo nor Modal VM Sandboxes has a desktop or computer-use API, so on both you set up a screen yourself; bochka streams a 60fps desktop with Chromium.
310th of 369, with limits
$2,210 a month
Can't run it6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
113th of 367, with limits
$1,105 a month
Can't run it7th 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
66th cheapest of 346
$748 a month
Can't run it6th 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
265th of 338, with limits
$14,966 a month
Can't run it71st 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
Islo's gateway can block hosts and log every call an attacking agent makes; Modal can block outbound traffic or allow only chosen domains.
47th of 360, with limits
$746 a month
294th of 360, with limits
$642 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

FeatureIsloModal VM Sandboxesbochka
IsolationA microVM with its own kernel per sandboxA VM with its own Linux kernel on Cloud HypervisorA full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker and nested virtualizationDocker inside and sudo; no /dev/kvm documentedDocker, systemd and root; /dev/kvm on Team and Enterprise only, on requestDocker, root, systemd and /dev/kvm on every plan
CPU benchmark (4 vCPU / 8 GB)Not measured15.54 runs/s26.69 runs/s
Longest sessionNo published cap; runs until you stop it or a timer you set fires24 hours (default 5 minutes)No cap on paid plans; you set the time to live
Pause and resumePause keeps files, processes and memory; can wake on the next exec, file access or webhookNo paused state; only Volumes and snapshots keep files after a sandbox endsStop for free and resume with the whole disk, saved every minute; resume reboots from disk
ForkSnapshot a running sandbox's files and start new sandboxes from itSnapshot the filesystem into an image and boot new sandboxes; memory snapshots in alphaFork a running sandbox with its disk
Desktop and computer useA browser for testing; no desktop or computer-use APINot offered; an example shows setting up Xvfb and VNC yourself60fps desktop, Chromium and a computer-use API built in
Coding agentsClaude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps on schedules and eventsExamples only; you install the agent yourselfClaude Code, Codex, OpenCode and more preinstalled, driven from outside with a prompt, steer and events API
Keeping keys out of the sandboxGateway injects stored credentials into outbound requests for any hostSecrets are environment variables, or you run your own proxy in a sidecarAI credentials proxy for model providers and any HTTPS API you register
Outbound network rulesAllow or deny by host, path and HTTP method, with per-request logsBlock all, IP-range allowlist, domain allowlist (beta)Open internet, no provider-side allowlist
Reaching the sandboxHTTPS share links that expire after a TTL; SSH and port-forward through the CLI; no raw TCPEncrypted and raw TCP tunnels, connect tokens, inbound IP allowlistHTTPS URLs for up to 50 ports, token-protected, plus raw TCP
Sandboxes at onceFree 5 and Team 50 running sandboxes per launch coverage; more by contract100 containers on Starter, 5,000 on Team100 to 2,000 running sandboxes by plan, raised by adding seats
RegionsUS West, or your own cloud account with BYOCUS, EU and Asia-Pacific; pinning costs 1.15x to 1.75xEU only: Germany, Finland, France, with EU data residency
Every feature Battleships tracks (43)
FeatureIsloModal VM Sandboxesbochka
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdNot publishedYesYes
Desktop GUINoNoYes
BrowserYesNoYes
Computer-use APINoNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesNoYes
Automatic snapshotsYesNoYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkNoYesNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesNoNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoYesYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesNoYes
Secret proxy for any APIYesNoYes
Preinstalled agentsYesNoYes
Agent harness APIYesNoYes
MCP serverNoNoNo
GPUNoNoNo
WindowsNoNoNo
Arm64NoNoNo
Self-hostingNoNoNo
BYOCYesNoNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)YesNot publishedYes
Audit logsYesYesNo
SSOYesYesNo
SOC 2Not publishedYesNo
HIPAANot publishedYesNo
EU data residencyNoYesYes
Zero data retentionNot publishedNot publishedYes

Performance

IsloNot measured
Modal VM Sandboxes15.54 runs/s
bochka26.69 runs/s

In StarSling's public run of 29 September 2026 at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 Node.js build-and-test runs per second and bochka did 26.69 on dedicated AMD Ryzen 9 9950X hosts, about 1.7 times the CPU work. Islo was not part of that run, so there is no comparable measurement for it.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Modal VM Sandboxes measured on: VM Sandbox, request = size. 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.

ScenarioIslo, a monthModal VM Sandboxes, a monthbochka, 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
$101 · Free$15 · Starter · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$420 · Free$178 · Starter · with limits$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
$4,863 · Team$2,229 · Starter · with limits$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
$1,382 · Team · with limits$792 · Team$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
$3,053 · Team · with limits$3,193 · Team · with limits$2,000 · $2000/mo · with limits

Islo: Islo bills each CPU core and each 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 you set at creation fires, and egress has no published price.

Modal VM Sandboxes: Modal bills by the second for the higher of the CPU and memory you request or use, until the sandbox ends. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and egress above the free allowance costs $0.04 per GiB.

Modal VM Sandboxes: bochka plans start at $20 a month and the whole fee becomes usage credit, spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

A Modal VM Sandbox lives at most 24 hours and only keeps files in a Volume or snapshot, so the workday, always-on and 50-agent scenarios do not fit it even though it prices lower than Islo there. Islo's Team plan is reported at 50 running sandboxes, so 300 user sandboxes and 1,000 short jobs at once need a custom contract; Modal's Team plan fits the 300. For 1,000 jobs at once, Modal's small CPU request is shared and not guaranteed, and bochka's start limits queue the burst.

ScenarioIsloModal VM Sandboxesbochka
One coding agent, workdays
  • egress price not published
  • files survive a stop only in Volumes: packages installed elsewhere reset
None that bite
One agent that never stops
  • egress price not published
  • Starter: sessions capped at 24 h
  • files survive a stop only in Volumes: packages installed elsewhere reset
None that bite
50 agents in parallel
  • egress price not published
  • files survive a stop only in Volumes: packages installed elsewhere reset
None that bite
Sandboxes for your users
  • Team: max 50 concurrent
  • egress price not published
None that biteNone that bite
1,000 short jobs at once
  • Team: max 50 concurrent
  • egress price not published
  • shared vCPUs on this tier (Modal (VM Sandboxes) sells dedicated cores separately as “VM Sandbox, request = size”): heavy, sustained CPU use can be slowed by other tenants
  • 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 Islo when

your agents run for days and must pause with memory, when you need per-host egress rules with a log of every call, or when it must run in the US or your own cloud account.

  • Agents that stay up and pause with memory. Useful for agents that run for days: Islo has no session cap and pauses idle sandboxes with memory kept.
  • 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.
  • Coding agents and your own cloud. Useful for teams running coding agents in the background: agents come preinstalled, and BYOC runs it all in your account.

Use Modal VM Sandboxes when

you run huge bursts of short jobs that finish within a day, need regions outside Europe, or already run your models on Modal.

  • Very large bursts. Useful for huge bursts of short jobs: Modal runs 5,000 containers at once on Team.
  • Regions and raw TCP. Useful if you need the US, EU or Asia-Pacific, or raw TCP tunnels into the sandbox.
  • One platform with inference and training. Useful if you already serve or train models on Modal: sandboxes and models share one account and one bill.

Where bochka fits

Look at bochka if your agents need more than a headless shell: a screen, emulators, or a machine they come back to for days. bochka gives every sandbox a full VM with /dev/kvm, a 60fps desktop and a disk that is saved every minute, with no session cap on paid plans.

A desktop agents can see and use

Neither Islo nor Modal VM Sandboxes has a desktop or computer-use API. An agent that must check a UI needs you to install Xvfb, VNC and a control layer in every image; bochka streams a 60fps desktop with Chromium.

/dev/kvm on every plan

Android emulators and tools that start their own VMs need /dev/kvm. Islo documents none, and Modal offers it only on Team and Enterprise after you ask support; bochka has it on every machine.

A faster VM that keeps its disk

A Modal VM ends within 24 hours and its root disk goes with it unless you write snapshot or Volume code. bochka keeps the whole disk across free stops and did 26.69 CPU runs per second against Modal's 15.54.

Use bochka when your agents need a desktop, /dev/kvm and ports you can host on, on a faster full VM in the EU that keeps its disk and never cuts them off. Compare it one to one: bochka vs Islo and bochka vs Modal VM Sandboxes.

Questions people ask

Is Islo cheaper than Modal VM Sandboxes?

In most of our scenarios Modal prices lower: one always-on agent comes to $178 a month on Modal against $420 on Islo, and 50 parallel agents $2,229 against $4,863. But Modal's VMs end within 24 hours, so those scenarios do not fit it. bochka comes to $26 and $317 for the same two.

Which is faster, Islo or Modal VM Sandboxes?

Islo has no public CPU measurement we can compare. In StarSling's benchmark at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 runs per second and bochka did 26.69.

Can Islo and Modal VM Sandboxes run Docker?

Yes, both run Docker inside their VMs. For Android emulators, Modal offers /dev/kvm on Team and Enterprise after you ask support, and Islo documents none. bochka has Docker and /dev/kvm on every plan.

How long can a sandbox run on each?

Islo publishes no session cap, so a sandbox runs until you stop it or a timer you set fires. A Modal VM Sandbox defaults to 5 minutes and stops at 24 hours at most. bochka has no session cap on paid plans.

Can I limit what an agent reaches on the internet?

Both can. Islo's gateway allows or denies by host, path and HTTP method and logs each request, while Modal can block all outbound traffic or allow only chosen IP ranges or domains. bochka has open internet with no provider-side allowlist.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview

More comparisons

Bochka product preview · Pricing, benchmarks and commands are illustrative. Sandbox provisioning is not connected.