Google Agent Runtime vs Islo
Google Agent Runtime hosts agents you build with ADK or LangGraph and gives them sandboxes that run as an unprivileged user in a locked container inside Google Cloud. Islo gives each coding agent its own microVM with sudo, Docker and SSH, with a gateway that controls and logs every outbound call.
The companies and products
Google Agent Runtime
Google Agent Runtime is the agent hosting part of Gemini Enterprise Agent Platform on Google Cloud, renamed from Vertex AI Agent Engine in April 2026.
It is a hyperscaler service, not a sandbox company. Agent Runtime deploys agents you build with ADK, LangGraph, LangChain, AG2 or LlamaIndex and bills them only while they work on a turn. Next to it, Agent Sandbox gives those agents a place to run code: a Code Execution sandbox, a shell or custom container sandbox, and a Computer Use browser. All of them run as secure containers inside your Google Cloud project.
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. “28th cheapest of 366” means 27 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 workload | Google Agent Runtime: price rank | Islo: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Islo runs Docker and sudo inside its microVMs, while Google's sandboxes have neither; boat adds /dev/kvm and a desktop on top, so emulators and screen tests run too. | 295th of 367, with limits $5,801 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 A Google sandbox is deleted when its TTL ends (7 days at most for a custom container), while an Islo or boat VM has no session cap. | 28th cheapest of 366 $7,519 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 Google fits best here, with a ready Python sandbox that has no network; Islo and boat both need higher start or concurrency limits for very large bursts. | 254th of 345, with limits $275 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 Google has no public URL for a user's sandbox and Islo's Team plan is reported at 50 running sandboxes, while boat serves HTTPS on up to 50 ports per sandbox. | 280th of 361, with limits $1,916 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 | 128th of 360, with limits $8,240 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; Google can branch many sandboxes from one memory snapshot. | 79th cheapest of 364 $2,060 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 can build containers with Docker inside, which Google's unprivileged sandboxes cannot; boat runs Docker and systemd on every VM. | 98th cheapest of 377 $989 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 Islo gives you SSH into a microVM that runs with no session cap, while Google has no SSH and runs each command in a new shell. | 311th of 368, with limits $241 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 Google offers a browser with a VNC view and a click and type API, Islo is headless with no computer-use API, and boat streams a full 60fps desktop. | 283rd of 369, with limits $1,648 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 | 102nd of 367, with limits $824 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 | 53rd cheapest of 346 $515 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 | 210th of 338, with limits $8,240 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 | 260th of 360, with limits $412 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 | Google Agent Runtime | Islo | boat |
|---|---|---|---|
| Isolation | Secure container sandboxing inside Google Cloud | A microVM with its own kernel for each sandbox | A full VM with its own kernel for each sandbox |
| Root and Docker | Runs as appuser with no sudo; images must not need root; no Docker | Sudo and Docker inside | Root, systemd and Docker on every machine |
| Nested virtualization | No /dev/kvm documented | No /dev/kvm or nested virtualization documented | /dev/kvm on every machine, for emulators and VMs inside |
| Shell access | execute_bash() API calls; each command runs in a new shell; no SSH | SSH and port-forward through the CLI | SSH, plus an API for commands |
| Desktop and computer use | A browser in a container with a VNC live view, a click, type and screenshot API, and CDP | A browser for testing; no desktop or computer-use API | 60fps desktop and Chromium, computer use and browser control, embeddable stream |
| Pause and memory | Pause keeps files; snapshots keep memory and files, and many sandboxes can start from one | Pause keeps files, processes and memory; wakes on the next exec, file access or webhook | Snapshots every minute and on stop; fork a running sandbox; resume reboots from disk |
| How long a sandbox lives | TTL of up to 7 days for a custom container and 14 days for Code Execution | No session cap | No session cap on paid plans |
| Reaching the sandbox | Through Google's API or a private endpoint in your VPC; no public URL documented | HTTPS share links anyone with the URL can open, expiring after a TTL (24 hours by default); no raw TCP | HTTPS URLs for up to 50 ports, token-protected; raw TCP; its own IP |
| Outbound internet rules | Off unless the template turns it on; route through your VPC with Cloud NAT, a static IP, Cloud NGFW or Secure Web Proxy | Gateway allows or denies by host, path and HTTP method, with default deny, rate limits and request logs | Open internet on every plan; no provider-side allowlist |
| Keeping keys out of the sandbox | You provision and scope the credentials the agent uses | Gateway injects stored credentials into outbound requests; they never reach the sandbox | AI credentials proxy for model providers and any HTTPS API; switch to another account when credits run out |
| Coding agents | Managed Agents API (Preview) runs Google's Antigravity harness | Claude Code, Cursor CLI and Codex preinstalled; factory lines with events and steer | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Hosting your agent code | Deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | You run your agent inside a sandbox | You run your own agent loop inside a sandbox |
| Sandboxes at once | Set by your Google Cloud project quota | Free 5 and Team 50 running sandboxes per launch coverage; more by contract | 100 to 2,000 running sandboxes by plan, raised by adding seats |
| Where it runs | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | US West, or inside your own cloud account with BYOC | EU only: Germany, Finland, France; EU data residency |
Every feature Battleships tracks (43)
| Feature | Google Agent Runtime | Islo | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | No | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | No | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | 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 | No | Yes | No |
| Wake on request | No | Yes | No |
| HTTPS preview URLs | No | Yes | Yes |
| Raw TCP inbound | Not published | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | No | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | Yes | No | No |
| Self-hosting | No | No | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | 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
There is no comparable measurement for either Google Agent Runtime or Islo: neither was part of StarSling's public sandbox benchmark run. In that run on 2026-09-29, boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB on dedicated AMD Ryzen 9 9950X hosts.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Google Agent Runtime and Islo have 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 | Google Agent Runtime, a month | Islo, a month | boat, 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 | $73 · Pay as you go | $101 · Free | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $301 · Pay as you go | $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 | $3,626 · Pay as you go · with limits | $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 | $1,030 · Pay as you go | $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 | $2,060 · Pay as you go | $3,053 · Team · with limits | $2,000 · $2000/mo · with limits |
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, rounded to the second, with the first 50 vCPU-hours and 100 GiB-hours free each month. Sandboxes bill while they exist, and disk, egress and paused rates are not published.
Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, with no plan fee and signup credits with no card. An idle sandbox bills until a pause-after-idle timer fires, and egress has no published price.
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
Google cannot run the 50-agent fleet because its sandboxes have no Docker, and every Google total leaves disk and egress out because those rates are not published. Islo's Team plan is reported at 50 running sandboxes, so 300 sandboxes for your users and 1,000 short jobs at once need a custom contract. On boat the 1,000-job burst gets queued, since starts are capped at 90 a minute and 2,400 a day on the $2,000 plan.
| Scenario | Google Agent Runtime | Islo | boat |
|---|---|---|---|
| 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 Google Agent Runtime when
you build agents with ADK or LangGraph on Google Cloud and want them hosted in your own project, network and region, with short code runs in a locked sandbox.
- A managed home for your agent code. Useful if you build agents with ADK or LangGraph: Agent Runtime hosts them and skips billing for idle time between turns.
- Memory snapshots you can branch. Useful for search and evals: a snapshot keeps memory and files, and many sandboxes can start from it.
- Regions worldwide, inside your project. Useful if agents must run in a Google Cloud perimeter, in one of 23 locations across six regions.
Use Islo when
your coding agents need a real VM with sudo, Docker and SSH, with per-host egress rules, a log of every outbound call and sandboxes that pause with memory.
- A real VM with sudo, Docker and SSH. Useful if agents run apt installs, Docker builds or compose stacks, or if you want to SSH in yourself.
- 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 boat fits
If your agents need a whole computer rather than a locked shell or a headless VM, look at boat. Each sandbox is a full VM with root, Docker, /dev/kvm, a desktop and public ports, with coding agents built in and no session cap on paid plans.
A desktop and nested virtualization
Google gives agents only a browser, and Islo is headless with no /dev/kvm documented. Android emulators, desktop apps and screen checks stall on both; boat has a 60fps desktop and /dev/kvm on every VM.
Ports a person can open
Google has no public URL, so a preview needs your own VPC endpoint or tunnel. Islo share links are open to anyone with the URL and expire after 24 hours by default. boat serves token-protected HTTPS on 50 ports and raw TCP.
Docker without a session clock
Google sandboxes have no Docker and are deleted when their TTL ends, so builds move elsewhere and long agents get recreated. Islo has Docker but caps Team at 50 running sandboxes; boat runs up to 2,000 with no session cap.
Use boat when your agents need a whole computer: root, Docker, /dev/kvm, a 60fps desktop and public ports on a full VM in the EU, with coding agents built in. Compare it one to one: boat vs Google Agent Runtime and boat vs Islo.
Questions people ask
Is Google Agent Runtime cheaper than Islo?
In our scenarios, yes: one coding agent on workdays comes to $73 a month on Google and $101 on Islo, and one agent running all month comes to $301 versus $420. boat comes to $20 and $26 for the same two. Google's totals leave out disk and egress, and Islo's leave out egress, since those rates are not published.
Which is faster, Google Agent Runtime or Islo?
We have no comparable CPU measurement for either one. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's public run of 2026-09-29.
Can Google Agent Runtime or Islo run Docker?
Islo can: its microVMs run Docker and sudo. Google's sandboxes run as the unprivileged user appuser with no sudo, so Docker is not available. boat runs root, Docker, systemd and /dev/kvm on every VM.
Are they containers or VMs?
Google runs its sandboxes as secure containers inside your Google Cloud project. Islo runs each agent in a microVM with its own kernel. boat gives every sandbox a full VM with its own kernel.
Can I limit what an agent reaches on the internet?
Both can. Google keeps outbound internet off unless the template turns it on and can route it through your VPC firewall, while Islo's gateway allows or blocks each host, path and method and logs every call. boat has open internet with no provider-side allowlist.
Where does my data run?
Google runs in 23 locations across the US, Europe, Asia, Canada, Australia and Brazil. Islo runs in US West, or in your own cloud account with BYOC. boat runs only in the EU (Germany, Finland and France).
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Google Agent Runtime
- boat vs Islo
- E2B vs Google Agent Runtime
- Daytona vs Google Agent Runtime
- Modal vs Google Agent Runtime
- Vercel Sandbox vs Google Agent Runtime
- Cloudflare Sandbox vs Google Agent Runtime
- Blaxel vs Google Agent Runtime
- Runloop vs Google Agent Runtime
- Tensorlake vs Google Agent Runtime
- Morph Cloud vs Google Agent Runtime
- CodeSandbox SDK vs Google Agent Runtime