Freestyle vs Google Agent Runtime
Freestyle sells full Linux VMs with root, Docker and memory pause, built for agents that each get their own machine. Google Agent Runtime, once called Vertex AI Agent Engine, hosts your agent code on Google Cloud and gives it sandboxes that run as an unprivileged user in a locked container.
The companies and products
Freestyle
Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.
Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.
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.
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. “40th cheapest of 345” means 39 of the other 344 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 | Freestyle: price rank | Google Agent Runtime: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Freestyle runs Docker, systemd and emulators but Google's sandboxes have no root or Docker; boat has all of them on faster CPUs. | 241st of 367, with limits $3,311 a month | 295th of 367, with limits $5,801 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Google fits an assistant that waits between turns, since Runtime skips idle time, but its sandboxes are deleted after 7 days; Freestyle and boat set no session cap. | 263rd of 366, with limits $4,195 a month | 28th cheapest of 366 $7,519 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 Freestyle fits short code runs well with VMs that pause with their memory and wake on the next request, and Google has a ready Python interpreter with no network. | 40th cheapest of 345 $482 a month | 254th of 345, with limits $275 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 Freestyle ranks 16th here because each user VM can sleep and wake on request; Google gives users no public URL, and boat ranks 1st with a desktop and hosting built in. | 16th cheapest of 361 $1,358 a month | 280th of 361, with limits $1,916 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 | 107th of 360, with limits $6,600 a month | 128th of 360, with limits $8,240 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 | 53rd cheapest of 364 $1,046 a month | 79th cheapest of 364 $2,060 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 Google's sandboxes cannot build containers without Docker, and Freestyle's docs send CPU-heavy jobs elsewhere; boat runs Docker on CPUs that did 2.8 times Freestyle's benchmark work. | 168th of 377, with limits $625 a month | 98th cheapest of 377 $989 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Freestyle offers SSH into a full VM, while Google runs each command through an API in a new shell; boat adds a desktop you can log into. | 98th cheapest of 368 $151 a month | 311th of 368, with limits $241 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 ships a browser with a VNC view and a click and type API, Freestyle has guides to install a desktop yourself, and boat streams a full 60fps desktop. | 234th of 369, with limits $940 a month | 283rd of 369, with limits $1,648 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 Google's Computer Use browser takes CDP for Playwright with egress off by default; on Freestyle you install Chromium and a display; boat has Chromium ready. | 257th of 367, with limits $482 a month | 102nd of 367, with limits $824 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 | 278th of 346, with limits $482 a month | 53rd cheapest of 346 $515 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 | 183rd of 338, with limits $6,560 a month | 210th of 338, with limits $8,240 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 | 272nd of 360, with limits $482 a month | 260th of 360, with limits $412 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 | Freestyle | Google Agent Runtime | boat |
|---|---|---|---|
| Isolation | Full KVM VM with its own kernel | Secure container sandboxing inside Google Cloud | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| CPU benchmark (4 vCPU / 8 GB) | 9.64 runs/s | No comparable measurement | 26.69 runs/s |
| Root, Docker and nested virtualization | Yes; systemd is pid 1, Docker runs from boot, full KVM support | Runs as appuser with no sudo; images must not need root; no Docker or /dev/kvm documented | Root, systemd, Docker and /dev/kvm on every machine |
| Desktop, browser and computer use | Guides to install GNOME or Xvfb, VNC and Chromium yourself | A browser in a container with a VNC view, a click, type and screenshot API, and CDP | Linux desktop streamed at 60fps, Chromium and computer use built in |
| How long a sandbox lives | No provider cap; a VM runs until you pause, stop or delete it | TTL of up to 7 days for a custom container and 14 days for Code Execution | No session cap on paid plans |
| Idle billing | A paused VM bills for its storage; no idle timeout unless you set one | Runtime skips idle time between turns; sandboxes bill while they exist, less when paused (rate not published) | A stopped sandbox costs nothing and keeps its disk |
| Memory pause, fork and wake | Pause with memory, clone a running VM, wake a paused VM on the next request | Snapshots keep memory and files; start many sandboxes from one snapshot; no wake on request | Fork a running sandbox with its disk; resume reboots from disk |
| Reaching the sandbox | SSH; HTTPS on style.dev names or your own domain, forward auth | Through Google's API or a private endpoint in your VPC; no SSH or public URL documented | SSH; HTTPS URLs for up to 50 ports, token-protected; raw TCP |
| Outbound rules | Default-deny firewall with allow rules by IP, VM, VPC or exact domain | Off unless the template turns it on; route through your VPC with Cloud NAT, Cloud NGFW or Secure Web Proxy | Open internet, no provider-side allowlist |
| Coding agents | claude, codex, opencode and openclaw preinstalled, driven through exec or a terminal | Managed Agents API (Preview) runs Google's Antigravity harness | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Credentials injected at the edge for HTTPS headers, Postgres and S3 | You provision and scope the credentials the agent uses | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Hosting your agent code | You run your own agent loop inside a VM | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents | You run your own agent loop inside a sandbox |
| Biggest machine | 32 vCPU / 64 GiB on Pro, 64 / 128 with custom limits | Runtime up to 8 vCPU and 32 GiB; sandbox maximum not published | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Regions | Not listed; the docs name a San Jose, US data center | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | EU only (Germany, Finland, France), zero data retention |
Every feature Battleships tracks (43)
| Feature | Freestyle | Google Agent Runtime | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | No | 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 | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | Yes | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | No | No | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | No | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Not published | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, Freestyle did 9.64 runs per second and boat did 26.69, so boat finished about 2.8 times as much CPU work in the same time. There is no comparable measurement for Google Agent Runtime or its sandboxes. Freestyle advertises VM starts in about 65 ms, which this test does not measure.
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 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 | Freestyle, a month | Google Agent Runtime, 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 | $27 · Free | $73 · Pay as you go | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $159 · Free | $301 · Pay as you go | $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 | $2,139 · Pro | $3,626 · Pay as you go · 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 | $581 · Pro | $1,030 · Pay as you go | $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 | $1,305 · Pro · with limits | $2,060 · Pay as you go | $2,000 · $2000/mo · with limits |
Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. On Free those allowances are hard stops; Hobby and Pro set a $50 or $500 monthly minimum that counts as usage.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, with the first 50 vCPU-hours and 100 GiB-hours free each month. Runtime skips idle time between turns, but sandboxes bill while they exist, and disk, egress and paused rates are not published.
Google Agent Runtime: 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
Freestyle Pro allows 400 concurrent VMs, so it does not fit 1,000 short jobs at once, and on Free the monthly allowances are hard stops. Google fits that burst, but its sandboxes have no Docker, so the 50-agent fleet does not fit, and every Google row leaves disk and egress unpriced. A Google sandbox is also deleted when its TTL ends, 7 days at most for a custom container. boat queues the burst: starts are capped at 90 a minute and 2,400 a day on the $2,000 plan.
| Scenario | Freestyle | Google Agent Runtime | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users | None that bite |
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Freestyle when
your agents need a full VM with root and Docker that can pause with its memory, wake on the next request or grow past 16 vCPU.
- A full VM with root and Docker. For agents that run apt, Docker or emulators: each Freestyle VM has its own kernel, systemd and nested virtualization.
- Memory pause and wake on request. For VMs that sleep between requests: they resume the same processes and wake on the next incoming traffic.
- Big machines. For heavy single jobs: Pro VMs go up to 32 vCPU / 64 GiB, and custom limits reach 64 / 128.
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 regions, with short code runs in a locked sandbox.
- A managed home for your agent code. For teams building with ADK or LangGraph: Agent Runtime hosts the agent and skips billing for idle time between turns.
- Inside your Google Cloud network. For agents that must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
- Regions worldwide. For teams that need the US, Asia or Brazil: Runtime and sandboxes run in 23 locations.
Where boat fits
If your agents do hours of real work, building, testing, running Docker and using a desktop, look at boat. It gives every agent a full VM like Freestyle, on CPUs that did 2.8 times Freestyle's benchmark work, with a desktop, public URLs and coding agents built in, none of which Google's locked sandboxes offer. It runs in the EU only, with no memory pause or wake on request.
Fast CPUs with root and Docker
Google's sandboxes have no root or Docker, so builds and compose stacks must run somewhere else. Freestyle has both, but did 9.64 benchmark runs per second against boat's 26.69, so every install and test waits longer.
A desktop and public URLs, ready
On Freestyle you install GNOME or Xvfb, VNC and Chromium yourself. Google gives only a browser and no public URL, so showing a preview means a VPC endpoint or tunnel. boat streams a 60fps desktop and serves HTTPS on 50 ports.
Coding agents driven from outside
Freestyle starts agent CLIs through exec and you parse the output; Google runs only its Antigravity harness, in Preview. boat drives Claude Code, Codex and others by API, and its credentials proxy switches accounts when credits run out.
Use boat when your agents do real work for hours: builds, tests, Docker, a desktop and a browser, on fast CPUs, with public URLs and an API to drive the coding agents inside from outside. Compare it one to one: boat vs Freestyle and boat vs Google Agent Runtime.
Questions people ask
Is Freestyle cheaper than Google Agent Runtime?
In our scenarios, mostly yes: one agent running all month is $159 on Freestyle against $301 on Google, and sandboxes for your users are $581 against $1,030. For 1,000 short jobs at once Google fits at $2,060 while Freestyle Pro caps at 400 concurrent VMs. boat comes to $26 a month and $200 a month for those first two.
Which is faster, Freestyle or Google Agent Runtime?
Freestyle did 9.64 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and Google's sandboxes have no comparable measurement. boat did 26.69 on the same test, about 2.8 times Freestyle's work.
Can Freestyle or Google Agent Runtime run Docker?
Freestyle can: each VM has root, systemd as pid 1 and Docker from boot. Google's sandboxes run as the unprivileged user appuser with no sudo, so Docker is not available. boat has root, Docker and /dev/kvm on every sandbox.
Is Google Agent Runtime the same as Vertex AI Agent Engine?
Yes. Google renamed Vertex AI Agent Engine to Agent Runtime in April 2026, as part of Gemini Enterprise Agent Platform. Its code, shell and browser sandboxes are a separate part called Agent Sandbox.
How long can a sandbox run?
Freestyle sets no provider cap, so a VM runs and bills until you pause, stop or delete it. A Google sandbox is deleted when its TTL ends, 7 days at most for a custom container and 14 days for Code Execution. boat has no session cap on paid plans.
Can I run a browser agent on either?
Google's Computer Use sandbox gives a browser with a VNC view, a click and type API and CDP for Playwright. On Freestyle you install Chromium, a virtual display and VNC yourself. boat ships a 60fps desktop, Chromium and computer use in every sandbox.
Try boat
Install the CLI, then run boat new.
7-day free trial