Daytona vs Islo

Daytona starts every sandbox as a container and sells Linux VM, Windows and GPU classes on top, in the US and the EU. Islo gives every agent its own microVM in US West or your own cloud, with a gateway that decides what each agent can reach.

The companies and products

Daytona

Daytona is a cloud for running AI-generated code: you create sandboxes from code through its API and SDKs.

By default a Daytona sandbox is a Linux container with its own namespaces and reserved vCPU, memory and disk. You can also pick a Linux VM class (pause, fork, memory snapshots, /dev/kvm), a Windows VM class, or a GPU class with Nvidia and AMD cards. It is built for teams that run agent code, code interpreters and evals through Python, TypeScript, Ruby, Go or Java SDKs.

Founded
2023

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. “15th cheapest of 367” means 14 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 workloadDaytona: price rankIslo: price rankbochka: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Daytona fits fully and Islo is a compromise: Islo runs Docker but documents no /dev/kvm or desktop, Daytona needs its Linux VM class for /dev/kvm, and bochka has both on every machine.
15th cheapest of 367
$4,111 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 with no session cap; Islo can pause an idle assistant with its memory and wake it on the next request, and Daytona's VM class auto-pauses after an hour idle.
24th cheapest of 366
$6,104 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
Daytona fits one-minute runs best: it creates 300 to 600 sandboxes a minute with no plan fee, while Islo needs a raised concurrency limit and bochka's start limits queue big bursts.
25th cheapest of 345
$271 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 of 2 vCPU at once is more than Daytona's Tier 4 pool of 500 vCPU and more than the 50 running sandboxes reported for Islo's Team plan, so both need custom limits; bochka fits.
154th of 361, with limits
$2,000 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
130th of 360, with limits
$8,261 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 built-in Harbor integration and gateway rules that stop trials from looking up answers, Daytona offers memory forks on its VM class, and bochka runs more sandboxes at once.
189th of 364, with limits
$2,000 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
Islo fits fully while Daytona caps one sandbox at 4 vCPU by default, so an 8 vCPU CI job needs a raised limit there; bochka allows 8 vCPU from the $20 plan.
308th of 377, with limits
$805 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
183rd of 368, with limits
$245 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
Daytona has a VNC desktop and a computer-use API on Linux and Windows, Islo sandboxes are headless, and bochka streams a 60fps desktop you can embed in your app.
26th cheapest of 369
$1,198 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
93rd of 367, with limits
$598 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
38th cheapest of 346
$404 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
202nd of 338, with limits
$8,073 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
12th cheapest of 360
$2,000 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
Only Daytona fits: it rents Nvidia and AMD GPUs by the hour, and neither Islo nor bochka has GPUs.
20th cheapest of 98
$1,190 a month
Can'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

FeatureDaytonaIslobochka
IsolationContainer by default; Linux VM and Windows VM classes with their own kernel on requestEvery sandbox is a microVM with its own kernelEvery sandbox is a full VM with its own kernel
CPU speed (Node.js build-and-test, 4 vCPU / 8 GB)21.52 runs/s on the Linux VM class; the default container class reported no resultNot measured in the public benchmark26.69 runs/s
Docker and nested virtualizationDocker in all classes; /dev/kvm only on Linux VMs, with KVM turned on for your organizationDocker inside and sudo; no /dev/kvm or nested virtualization documentedDocker, root, systemd and /dev/kvm on every machine
Desktop and computer useVNC desktop (xfce4) and a computer-use API on Linux and WindowsA browser inside the sandbox for testing; no desktop or computer-use API60fps desktop and Chromium, computer use and browser control, embeddable stream
Pause and wakeLinux VM and Windows classes pause and resume with memory kept; containers cannot pausePause keeps files, processes and memory; can pause after idle time and wake on the next exec, file access or webhookStop and resume; resume reboots from disk (no memory snapshots)
ForkLinux VM and Windows classes fork with memory kept; containers cannot forkSnapshot a running sandbox's files, then start new sandboxes from itFork a running sandbox into new ones
Files after a stopThe disk is kept and billed while stopped; archived containers are freeFiles kept; whether stopped disk is billed is unclear (the FAQ says no charge, but storage has its own meter)Snapshots every minute and on stop; a stopped sandbox costs nothing
Reaching the sandboxHTTPS preview URLs on any port, token-protected or public; SSH; no raw TCP or public IPHTTPS share links anyone with the URL can open, expiring after 24 hours by default; SSH and port-forward through the CLIHTTPS URLs for up to 50 ports, token-protected; raw TCP; its own IP
Outbound internet rulesTier 1 and 2 reach only package registries, git hosts and AI APIs; Tier 3 and up get open internet plus per-sandbox domain or CIDR allowlistsGateway profiles allow or deny by host, path and HTTP method, with default deny, rate limits and per-request logsOpen internet on every plan; no provider-side allowlist
Keeping keys out of the sandboxSecrets proxy swaps placeholders in HTTPS request headers for allowed hostsGateway injects stored credentials into outbound requests for any hostAI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out
Coding agentsGuides install agents and run them through process execClaude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps with events, steer and follow-upsClaude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
GPUs and WindowsNvidia and AMD GPUs on-demand or preemptible; Windows VM sandboxesNo GPUs; Linux onlyNo GPUs; Linux VMs, with Wine for Windows apps
Sandboxes at onceAn org-wide pool of 10, 100, 250 or 500 vCPU from Tier 1 to Tier 4, not a sandbox countFree 5 and Team 50 running sandboxes per launch coverage; paused ones do not count100 to 2,000 running sandboxes by plan, raised by adding seats
Where it runsUS and EU, plus dedicated regions or your own machinesUS West, or inside your own cloud account with BYOCEU only: Germany, Finland, France; EU data residency
Every feature Battleships tracks (43)
FeatureDaytonaIslobochka
Full VM (own kernel)NoYesYes
Docker insideYesYesYes
Nested virtualizationYesNoYes
RootYesYesYes
SystemdNot publishedNot publishedYes
Desktop GUIYesNoYes
BrowserYesYesYes
Computer-use APIYesNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)NoYesYes
Memory forkYesNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestNoYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APINoYesYes
MCP serverYesNoNo
GPUYesNoNo
WindowsYesNoNo
Arm64NoNoNo
Self-hostingNoNoNo
BYOCYesYesNo
Open sourceNoNoNo
Scoped API keysYesNot publishedYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)YesYesYes
Audit logsYesYesNo
SSOYesYesNo
SOC 2YesNot publishedNo
HIPAAYesNot publishedNo
EU data residencyYesNoYes
Zero data retentionNot publishedNot publishedYes

Performance

Daytona21.52 runs/s
IsloNot measured
bochka26.69 runs/s

In StarSling's public run of 2026-09-29 at 4 vCPU / 8 GB, bochka did 26.69 Node.js build-and-test runs per second and Daytona's Linux VM class did 21.52. Daytona's default container class reported no result in that run. Islo was not part of it, so there is no comparable number for Islo.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Daytona measured on: Linux VM sandbox (same rates; KVM / nested virt per-org feature). 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.

ScenarioDaytona, a monthIslo, 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
$56 · Tier 3 ($500 top-up)$101 · Free$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$245 · Tier 3 ($500 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
$2,682 · Tier 3 ($500 top-up)$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
$2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits$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
$2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits$3,053 · Team · with limits$2,000 · $2000/mo · with limits

Daytona: Daytona bills per second for the vCPU, memory and disk you reserve, including while a sandbox starts or stops, and keeps billing the disk while it is stopped. You pay from a prepaid wallet: open internet needs a $500 top-up (Tier 3), and the biggest pool needs $2,000 every 30 days (Tier 4).

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 fires, and that timer can only be set when the sandbox is created.

Islo: 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.

Limits in those scenarios

Daytona limits the total vCPU, memory and disk running at once (500 vCPU at Tier 4), and Islo's Team plan is reported at 50 running sandboxes. So 300 sandboxes for your users and 1,000 short jobs at once fit neither without a custom limit. Daytona also caps one sandbox at 4 vCPU / 8 GB by default and only opens the internet from Tier 3. Neither publishes an egress price, so their totals here leave egress out.

ScenarioDaytonaIslobochka
One coding agent, workdays
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
  • egress price not published
None that bite
One agent that never stops
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
  • egress price not published
None that bite
50 agents in parallel
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
  • egress price not published
None that bite
Sandboxes for your users
  • max 500 vCPU running at once (needs 600)
  • max 1,000 GiB running at once (needs 1,200)
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
  • Team: max 50 concurrent
  • egress price not published
None that bite
1,000 short jobs at once
  • max 500 vCPU running at once (needs 2,000)
  • max 1,000 GiB running at once (needs 4,000)
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
  • 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 Daytona when

your agents need GPUs, Windows or forks that keep memory, or must run in both the US and the EU, and containers by default are fine for you.

  • GPUs by the hour. Useful if your agents train or test models: Daytona rents Nvidia and AMD GPUs by the hour, from RTX 4090 to B300.
  • Windows and memory forks. Useful if you need Windows desktops or forks that keep memory: Daytona's VM classes do both.
  • US, EU and your own machines. Useful if you need both US and EU regions: Daytona runs in each and can also run sandboxes on machines you bring.

Use Islo when

every agent must get its own VM by default, with per-host egress rules, a log of every outbound call, and sandboxes that pause with memory and wake on request.

  • A VM for every agent by default. Useful if you want kernel isolation without picking a class: every Islo sandbox is a microVM with its own kernel.
  • 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.

Where bochka fits

If your agents do long, real work like installs, builds, tests, Docker and emulators, and you can run in the EU, bochka is worth a look before either. Every bochka sandbox is a full VM with /dev/kvm, a desktop and ports you can host on, and it ran faster than Daytona in the one public test that measured both.

A full VM with /dev/kvm on every machine

Daytona's default sandbox is a container that shares the host kernel, and /dev/kvm needs its VM class plus KVM turned on for your organization. Islo has VMs but documents no /dev/kvm, so Android emulators stop at the first boot.

Ports you can host on

Daytona has no raw TCP or public IP, and Islo share links are open to anyone with the URL and expire after 24 hours by default. bochka serves up to 50 token-protected HTTPS ports and raw TCP for as long as the sandbox lives.

Room for a fleet with open internet

Daytona opens the internet only from Tier 3, a $500 top-up, and its biggest pool is 500 vCPU. Islo's Team plan is reported at 50 running sandboxes. bochka has open internet on every plan and 100 to 2,000 sandboxes by plan.

Use bochka when your agents do real work for hours: installs, builds, tests, Docker and emulators on a full, faster VM with a desktop, ports you can host on and coding agents built in. Compare it one to one: bochka vs Daytona and bochka vs Islo.

Questions people ask

Is Daytona cheaper than Islo?

In the scenarios we priced, yes: one coding agent on workdays comes to $56 a month on Daytona and $101 on Islo, and one agent running all month comes to $245 versus $420. 50 agents in parallel come to $2,682 versus $4,863. On bochka the same three come to $20, $26 and $317 a month.

Which is faster, Daytona or Islo?

There is no head-to-head number. In StarSling's public run, Daytona's Linux VM class did 21.52 runs per second and bochka did 26.69; Islo was not tested, and Daytona's default containers reported no result.

Are Daytona and Islo sandboxes containers or VMs?

Daytona's default sandbox is a Linux container, with Linux VM and Windows VM classes you can choose. Every Islo sandbox is a microVM with its own kernel, built from a container image. bochka gives every sandbox a full VM.

Can Daytona and Islo run Docker?

Yes, both run Docker inside a sandbox. Daytona gives /dev/kvm only on its Linux VM class with KVM turned on for your organization, and Islo documents no /dev/kvm. bochka has Docker, systemd and /dev/kvm on every machine.

Can I limit what an agent reaches on the internet?

On both. Daytona from Tier 3 lets you limit each sandbox to chosen domains or IP ranges, and Islo's gateway allows or denies by host, path and HTTP method and logs each request. bochka has open internet with no provider-side allowlist, and its credentials proxy keeps real API keys out of the sandbox.

Where do Daytona and Islo run?

Daytona runs in the US and the EU, plus dedicated regions and your own machines. Islo runs in US West, or inside your own cloud account with BYOC. bochka runs only in the EU (Germany, Finland and France), with EU data residency.

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.