E2B vs Islo
Both give each agent its own microVM with its own kernel, and both can pause with memory and wake on the next request. E2B is built for huge numbers of short jobs with a 24-hour session cap, while Islo keeps sandboxes running as long as you want and checks every outbound request at a gateway.
The companies and products
E2B
E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.
Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs, and its runtime is open source.
- Isolation
- Firecracker microVM per sandbox
- Bring your own cloud
- Enterprise data plane in your AWS, GCP or Azure account
- Compliance
- SOC 2 Type II; HIPAA BAA on request
- Machine size
- 1 to 8 vCPU and 1 to 8 GiB RAM, CPU only
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. “16th cheapest of 367” means 15 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 | E2B: price rank | Islo: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month E2B fits this well and Islo is a compromise, while bochka adds /dev/kvm, a desktop and no session cap on a faster CPU. | 16th cheapest of 367 $4,143 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 An assistant that lives on its machine all month hits E2B's 24-hour cap, while Islo and bochka keep it running with no cap. | 51st of 366, with limits $5,348 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 E2B is built for short code runs that start fast and pause with memory; Islo needs a raised concurrency limit for big bursts. | 37th cheapest of 345 $421 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 fits E2B Pro+ but is more than the 50 running sandboxes reported for Islo's Team plan. | 23rd cheapest of 361 $2,354 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 E2B ranks 2nd here, with memory forks and a high start rate for many short rollouts; Islo's 50-sandbox Team limit holds it back. | 2nd cheapest of 360 $9,384 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 | 78th cheapest of 364 $1,975 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 CI runners with no session cap, while E2B is a compromise; neither has /dev/kvm for Android or VM builds, which bochka has. | 337th of 377, with limits $1,429 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 A dev box that runs all month fits Islo and bochka, since neither caps the session, while E2B stops at 24 hours. | 192nd of 368, with limits $358 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 E2B has a Linux desktop for computer use and Islo sandboxes are headless; bochka streams a 60fps desktop you can embed. | 32nd cheapest of 369 $1,342 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 | 100th of 367, with limits $746 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 | 57th cheapest of 346 $554 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 | 227th of 338, with limits $9,223 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 | 11th cheapest of 360 $1,043 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 it | 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 | Can't run it |
Key features
| Feature | E2B | Islo | bochka |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | MicroVM with its own kernel, built from a container image | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| CPU benchmark (4 vCPU / 8 GB) | 12.61 runs/s | Not measured | 26.69 runs/s |
| Session length | Up to 1 hour on Hobby, 24 hours on Pro; pausing resets the clock | No published cap; runs until you stop it or a lifecycle rule fires | No cap on paid plans; you set the time to live |
| Pause and resume | Saves memory and disk; resumes in about a second, and can wake on the next HTTP request or SDK call | Keeps files, processes and memory; can pause after idle time and resume on the next exec, file access or webhook | Disk saved every minute and on stop; a stopped sandbox costs nothing; resume boots from disk |
| Fork | Fork a running sandbox with its memory, up to 20 copies per call | Snapshot a running sandbox's files, then start new sandboxes from it | Fork a running sandbox with its disk |
| Docker and nested virtualization | Docker inside; nested virtualization not supported | Docker inside and sudo; no /dev/kvm documented | Docker, root, systemd and /dev/kvm on every machine |
| Desktop and computer use | Linux desktop for computer use | A browser for testing; no desktop or computer-use API | 60fps desktop with Chromium, computer-use API and an embeddable stream |
| Reaching the sandbox | HTTPS URL per port, public unless you turn on a token; no dedicated IP | HTTPS share links that expire after a TTL (24 hours by default); SSH and port-forward through the CLI | HTTPS URLs for up to 50 ports, token-protected; raw TCP; its own IP |
| Outbound internet rules | Allow and deny lists by IP, CIDR or domain | Gateway rules by host, path and HTTP method, with default deny, rate limits and content filters | Open internet, no provider-side allowlist |
| Keeping keys out of the sandbox | Secrets injected into outbound HTTPS headers (private beta) | Gateway injects stored credentials into outbound requests for any host | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Coding agents | Templates and guides for many agents, run through the command API | Claude Code, Cursor CLI and Codex preinstalled; factory lines with events, steer and follow-ups | Seven agents preinstalled, with a prompt, steer and events API |
| Sandboxes at once | 20 on Hobby, 100 on Pro, up to 1,100 self-serve with add-ons | 5 on Free and 50 on Team per launch coverage; more by contract | 100 to 2,000 running sandboxes by plan |
| Where it runs | US, EU and APAC; open-source runtime and bring your own cloud on Enterprise | US West, or inside your own cloud account with BYOC | EU only: Germany, Finland, France; EU data residency |
Every feature Battleships tracks (43)
| Feature | E2B | Islo | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | Yes | No | No |
| BYOC | Yes | Yes | No |
| Open source | Yes | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Yes | No |
| SSO | No | Yes | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | Yes | Not published | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's run of 2026-09-29 at 4 vCPU / 8 GB, bochka did 26.69 Node.js build-and-test runs per second and E2B did 12.61, so bochka finished about twice as much CPU work. Islo was not part of that run, so there is no comparable measurement for it. This measures CPU speed only, not start time.
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 | E2B, a month | Islo, a month | bochka, 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 | $202 · Pro | $101 · Free | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $368 · Pro · with limits | $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 | $2,773 · Pro | $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 | $1,395 · Pro+ (600 concurrent) | $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 | $2,797 · Pro++ (1,100 concurrent) | $3,053 · Team · with limits | $2,000 · $2000/mo · with limits |
E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox. Pro costs $150 a month for higher limits with no usage credit, and more concurrency costs $500 a month per 500 slots.
Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, billed per hour, with no plan fee and signup credits with no card. An idle sandbox keeps billing until a pause-after-idle timer fires, and egress has no published price.
Islo: Plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
E2B caps a session at 24 hours on Pro, so an agent that runs all month does not fit without pausing and resuming. Islo has no session cap, but its 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. E2B Pro++ handles the 1,000-job burst but queues bursts above 300 starts a minute. bochka's start limits also queue that burst and need more starts per day than its $2,000 plan allows.
| Scenario | E2B | Islo | bochka |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use E2B when
you run very large numbers of short jobs or RL rollouts, need memory forks or a desktop, or must run in the EU or APAC.
- Built for huge numbers of short jobs. For bursts and RL rollouts, E2B sells up to 1,100 sandboxes at once self-serve and forks a running sandbox with its memory.
- A desktop for computer use. For agents that need a screen, E2B has a Linux desktop for computer use, while Islo sandboxes are headless.
- More regions and an open runtime. For teams outside the US, E2B runs in the US, EU and APAC, and its runtime is open source under Apache-2.0.
Use Islo when
your agents run for days in the US or your own cloud, and you need gateway rules and a log of every outbound call.
- No session cap. For agents that work for days, an Islo sandbox keeps running until you stop it, while E2B stops at 24 hours on Pro.
- Egress rules and request logs. For teams that must control what agents reach, Islo checks each host, path and method and logs every call.
- Coding agents ready to run. For background coding work, Islo ships Claude Code, Cursor CLI and Codex preinstalled, with factory lines triggered by GitHub, Slack or Linear.
Where bochka fits
If your agents do real work for hours, with builds, tests, Docker, emulators and a browser, look at bochka. It gives each one a full VM with /dev/kvm, a 60fps desktop and ports you can host on, with no session cap on paid plans. It is the better choice for long, heavy agent work, while E2B stays stronger for very large bursts of short jobs.
Faster machines with /dev/kvm
On the same CPU benchmark bochka did 26.69 runs per second and E2B did 12.61, and Islo was not measured. Neither E2B nor Islo offers /dev/kvm, so Android emulators and VMs inside the sandbox do not start.
Ports you can actually host on
E2B URLs are public unless you add a token and Islo share links expire after 24 hours by default, and neither has raw TCP. bochka serves up to 50 ports over HTTPS with tokens, plus raw TCP and its own IP.
A desktop and no session cap together
E2B has a desktop but cuts sessions at 24 hours, so your code must pause and resume. Islo runs without a cap but has no screen. bochka gives a 60fps desktop with computer use and no cap on paid plans.
Use bochka when your agents do hours of real work: builds, Docker, emulators and a desktop, on a fast full VM with ports you can host on and no session cap. Compare it one to one: bochka vs E2B and bochka vs Islo.
Questions people ask
Is E2B cheaper than Islo?
It depends on the job. One coding agent on workdays comes to $202 a month on E2B and $101 on Islo, but 50 agents in parallel come to $2,773 on E2B and $4,863 on Islo. bochka comes to $20 and $317 for the same two.
Which is faster, E2B or Islo?
E2B did 12.61 runs per second on StarSling's CPU benchmark at 4 vCPU / 8 GB, and Islo has no public measurement. bochka did 26.69 in the same run.
Can E2B and Islo run Docker?
Yes, both run Docker inside the sandbox. Neither offers nested virtualization, so Android emulators and VMs need bochka, which exposes /dev/kvm on every machine.
Can an E2B or Islo sandbox run for days?
Islo has no published session cap, so a sandbox runs until you stop it. E2B stops a sandbox after 24 hours on Pro and 1 hour on Hobby, though pausing resets the clock. bochka has no session cap on paid plans.
Which has a desktop for computer use?
E2B has a Linux desktop for computer use, while Islo sandboxes are headless with a browser for tests. bochka streams a 60fps desktop with Chromium and a computer-use API on every sandbox.
Can I control what the agent reaches on the internet?
Both can. E2B allows or denies traffic by IP, CIDR or domain, and Islo's gateway goes further with rules by host, path and HTTP method plus a log of every request. bochka has open internet with no provider-side allowlist.
Try bochka
Install the CLI, then run bochka new.
Product preview