Google Agent Runtime vs Unikraft Cloud

Google Agent Runtime hosts the agent code you build with ADK or LangGraph and gives it sandboxes that run as an unprivileged user in a locked container inside your Google Cloud project. Unikraft Cloud turns a Dockerfile into a tiny Firecracker microVM that boots in milliseconds, sleeps when traffic stops and is sold as flat pools of running capacity.

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.

Kind of product: Managed agent hosting plus code, shell and browser sandboxes on Google Cloud
Former name: Vertex AI Agent Engine, renamed Agent Runtime in April 2026
Isolation: Secure container sandboxing; commands run as the unprivileged user appuser with no sudo
Launch stage: Shell and Computer Use sandboxes GA since 2026-09-09; custom containers, templates and snapshots launched in Preview on 2026-05-26
Regions: 23 locations across the US, Europe, Asia, Canada, Australia and Brazil
Billing: $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, first 50 vCPU-hours and 100 GiB-hours free each month

Unikraft Cloud

Unikraft Cloud is a microVM cloud from Unikraft Inc. that runs any Dockerfile-based workload as a minimal Linux microVM with millisecond cold starts and scale-to-zero.

Your Dockerfile becomes the VM image at build time, and each instance runs on a heavily customized Firecracker VMM, so it boots in milliseconds and can go into standby when no traffic arrives. It is a general compute platform built for dense, bursty work such as HTTP services, headless browsers and agent fleets, sold as flat self-serve plans plus Enterprise dedicated hosts, on-prem and bring your own cloud. It is not a dev machine you log into: instances are reached through services, the CLI and a sandbox plugin for commands and files.

Isolation: Linux microVM per instance on a customized Firecracker VMM; full VMs on Enterprise
Plans: Hobby free, Team $39/mo, Pro $199/mo, Enterprise custom; each caps running instances, vCPUs and memory
Running capacity: 2 / 8 / 24 running instances with 4 / 8 / 32 GiB memory in total on Hobby / Team / Pro
Regions: Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default; more metros on request
Self-hosting: Dedicated host fleet, on-prem and BYOC on Enterprise
Compliance: SOC2, HIPAA and audit logs listed on Enterprise
Open source: The unikraft CLI is open source; the cloud platform is commercial

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	Unikraft Cloud: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Neither runs Docker inside a sandbox: Google's run as appuser with no sudo, and Unikraft builds your Dockerfile into the VM itself; bochka has root, Docker and systemd on every VM.	295th of 367, with limits $5,801 a month	Can't run it	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, and Unikraft's Team pool is 8 GiB shared by every running instance; a bochka VM has no session cap on paid plans.	28th cheapest of 366 $7,519 a month	Can't run it	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 Short code runs suit both: Google has a ready Python Code Execution sandbox, and Unikraft instances sleep between calls and wake in milliseconds, though self-serve plans cap you at 24 running ones.	254th of 345, with limits $275 a month	Can't run it	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 can serve users through its API but documents no public URL, and Unikraft Pro holds only 24 running instances, so hundreds of active users need Enterprise; bochka serves HTTPS on up to 50 ports per sandbox.	280th of 361, with limits $1,916 a month	Can't run it	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	Can't run it	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	79th cheapest of 364 $2,060 a month	Can't run it	10th cheapest of 364 $200 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Jobs that build Docker images need a container runtime that neither documents inside a sandbox, and Unikraft keeps nested virtualization for Enterprise; bochka has Docker and /dev/kvm on every plan.	98th cheapest of 377 $989 a month	Can't run it	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither offers SSH today, so you work through Google's execute_bash() API or Unikraft's CLI and sandbox plugin; Unikraft's Team pool comes to $39 a month against $241 on Google, and bochka gives you SSH and a desktop for $26 a month.	311th of 368, with limits $241 a month	219th of 368, with limits $39 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 gives agents a browser with a VNC view and a click and type API, Unikraft has nothing built in, and bochka streams a full 60fps desktop with Chromium.	283rd of 369, with limits $1,648 a month	Can't run it	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 runs a real Chromium you can drive over CDP with Playwright; on Unikraft you package your own headless browser in a Dockerfile; bochka has Chromium on a desktop out of the box.	102nd of 367, with limits $824 a month	Can't run it	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	Can't run it	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	Can't run it	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	Can't run it	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	Unikraft Cloud	bochka
Isolation	Secure container sandboxing inside your Google Cloud project	Minimal Linux microVM per instance on a customized Firecracker VMM	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Root and Docker inside	Runs as appuser with no sudo; images must not need root; no Docker documented	Runs as root; the Dockerfile becomes the VM image, with no container runtime inside documented	Root, systemd and Docker, like any Ubuntu machine
Nested virtualization	No /dev/kvm documented	Per-instance flag and permission, Enterprise only	/dev/kvm for Android emulators and VMs on every plan
Shell access	execute_bash() API calls; each command runs in a new shell; no SSH	No SSH yet; commands and files go through the sandbox plugin and CLI	SSH into every sandbox, plus an API for commands
Desktop and browser	A browser in a container with a VNC live view, a click, type and screenshot API, and CDP	None built in; you can run your own headless browser from a Dockerfile	Linux desktop streamed at 60fps, Chromium, computer use and browser control
Idle and wake	Pause keeps the file system at a lower rate Google does not publish; no wake on request	Standby after a 1 second idle cooldown by default, memory kept in stateful mode, woken by the next request in milliseconds	Disk saved every minute and on stop; a stopped sandbox costs nothing and is started again by API
How long a sandbox lives	TTL of up to 7 days for a custom container and 14 days for Code Execution, then deleted	No published maximum; instances run until stopped or go into standby	No session cap on paid plans
Memory snapshots and branching	Snapshots keep memory and files; start many sandboxes from one snapshot	Checkpoint memory and volumes of a running microVM with a pause of a few milliseconds, then start new instances from it	Fork a running sandbox with its disk; resume reboots from disk (no memory snapshots)
Inbound access	Through Google's API, or a private endpoint in your own VPC; no public URL documented	Services on its load balancer: HTTP on 80, HTTPS on 443, TLS-wrapped TCP on other ports; no public IP per instance	HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv4 or IPv6
Outbound rules	Off unless the template turns it on; route through your VPC with Cloud NAT, a static IP, Cloud NGFW or Secure Web Proxy	Network shield filters traffic, Enterprise only, limited access	Open internet on every plan; no provider-side allowlist
Keeping API keys out of the sandbox	You provision and scope the credentials the agent uses	Network shield can inject secrets into traffic, Enterprise only, limited access	Credentials proxy for model providers and any HTTPS API, on every plan; switch a credential to another account when credits run out
Coding agents and agent hosting	Agent Runtime hosts ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; Managed Agents API (Preview) runs Google's Antigravity harness	None preinstalled; you bring the agent in your own image	Claude Code, Codex, OpenCode and more preinstalled, driven from outside with a prompt, steer and events API
Machine size	Runtime: 1 to 8 vCPU and up to 32 GiB; sandbox maximum not published	Plan pool shared by all running instances: 2 vCPU / 4 GiB, 8 vCPU / 8 GiB or 24 vCPU / 32 GiB	Up to 8 vCPU / 16 GB on the $20 plan, 16 vCPU / 32 GB from the $100 plan
Regions	23 locations in the US, Europe, Asia, Canada, Australia and Brazil	Dallas, Frankfurt, San Francisco, Singapore and Washington DC, more on request	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

Feature	Google Agent Runtime	Unikraft Cloud	bochka
Full VM (own kernel)	No	Yes	Yes
Docker inside	No	No	Yes
Nested virtualization	No	Yes	Yes
Root	No	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	Yes	No	Yes
Computer-use API	Yes	No	Yes
SSH	No	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	No	Yes	No
Wake on request	No	Yes	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	Not published	Not published	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	No	Yes
Agent harness API	Yes	No	Yes
MCP server	No	No	No
GPU	No	Yes	No
Windows	No	No	No
Arm64	Yes	Yes	No
Self-hosting	No	Yes	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	No	Yes
Audit logs	Not published	Yes	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	Yes	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

Google Agent RuntimeNot measured

Unikraft CloudNot measured

bochka26.69 runs/s

There is no comparable CPU measurement for Google Agent Runtime or Unikraft Cloud: neither was part of the StarSling hpc-sandbox-benchmarks run. In that run bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Unikraft states cold starts under 10 ms, which is its own figure and measures start time, not CPU speed.

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 Unikraft Cloud 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	Unikraft Cloud, 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	$73 · Pay as you go	$39 · Hobby	$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	$39 · Hobby	$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	Can't run it	$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	Can't run it	$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	Can't run it	$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 are billed while they exist, and disk, egress and paused rates are not published.

Unikraft Cloud: Unikraft charges a flat monthly fee for a pool of running capacity: free for 2 vCPU / 4 GiB, $39 for 8 vCPU / 8 GiB, $199 for 24 vCPU / 32 GiB, with sleeping instances not counted. It publishes no per-hour rate, so anything bigger is an Enterprise quote.

Unikraft Cloud: 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

On Google, a sandbox is deleted when its TTL ends, so an agent that never stops has to be recreated, and the 50-agent fleet does not fit because there is no Docker inside. Unikraft's limits are shared pools: the Team pool of 8 vCPU and 8 GiB is filled by one 4 vCPU / 8 GB agent, so the fleet, user-sandbox and burst scenarios need an Enterprise contract. Neither publishes disk or egress prices. On bochka the 1,000-job burst is the problem: the $2,000 plan caps starts at 90 a minute and 2,400 a day, so jobs get queued.

Scenario	Google Agent Runtime	Unikraft Cloud	bochka
One coding agent, workdays	disk beyond 0 GiB: price unknown egress price not published	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown egress price not published	None that bite
One agent that never stops	disk beyond 0 GiB: price unknown egress price not published	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown egress price not published	None that bite
50 agents in parallel	missing Docker inside disk beyond 0 GiB: price unknown egress price not published	no pool tier with 200 vCPU / 400 GiB for 50 VMs no published per-resource rate	None that bite
Sandboxes for your users	disk beyond 0 GiB: price unknown egress price not published	no pool tier with 600 vCPU / 1,200 GiB for 300 VMs no published per-resource rate	None that bite
1,000 short jobs at once	disk beyond 0 GiB: price unknown egress price not published	no pool tier with 2,000 vCPU / 4,000 GiB for 1,000 VMs no published per-resource rate	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 Google Agent Runtime when

you build agents with ADK or LangGraph on Google Cloud and want them hosted inside your own project, network rules and regions, 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.
Inside your Google Cloud network. Useful if agents must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
Many regions, ready browser. Useful if you need 23 locations worldwide or a browser sandbox with a live view and a click and type API.

Use Unikraft Cloud when

you run many small services or headless browsers that sleep most of the time and must wake in milliseconds, or want GPUs, on-prem or your own cloud under an Enterprise contract.

Millisecond starts and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
Root and a flat monthly pool. Useful if you want root in a real microVM and a known monthly bill, with a free Hobby plan to start.
GPUs and your own hardware. Enterprise customers can get NVIDIA GPUs, arm64 hosts, dedicated hosts, on-prem or their own cloud.

Where bochka fits

Google Agent Runtime is built to host agent code, and Unikraft Cloud is built for tiny services that sleep and wake fast. If what you are really running is agents that need a whole computer to work in, with Docker, SSH, a desktop and public URLs, look at bochka. Each bochka sandbox is a full VM that keeps its disk, with coding agents built in.

Root, Docker and /dev/kvm

Google runs commands as appuser with no sudo, and Unikraft builds your Dockerfile into the VM with no container runtime inside. On both you bake every tool into an image up front, and Unikraft's nested virtualization needs Enterprise.

SSH and public URLs

Neither offers SSH today. Google documents no public URL, so you set up a VPC endpoint or tunnel yourself, and Unikraft exposes only load balancer services. bochka gives SSH, HTTPS on 50 ports and raw TCP.

Coding agents and keys kept outside

Google's Managed Agents API runs only its Antigravity harness, in Preview, and Unikraft has no agents built in, with secret injection Enterprise only. bochka ships Claude Code and Codex and keeps real keys in a credentials proxy.

Use bochka when your agents need a real machine to work in: root, Docker, SSH, a desktop and public URLs on a full VM that keeps its disk, with Claude Code, Codex and other coding agents driven from outside. Compare it one to one: bochka vs Google Agent Runtime and bochka vs Unikraft Cloud.

Questions people ask

Is Google Agent Runtime cheaper than Unikraft Cloud?

For one agent, no: one coding agent on workdays comes to $73 a month on Google and $39 on Unikraft's Team pool, and one agent running all month to $301 against $39. bochka comes to $20 and $26 for the same two. For 50 agents, sandboxes for your users or 1,000 short jobs, no self-serve Unikraft plan is big enough, so the price is an Enterprise quote.

Which is faster, Google Agent Runtime or Unikraft Cloud?

Neither has a comparable CPU measurement, so we cannot say which computes faster. Unikraft is built to start fast: its microVMs cold boot in milliseconds and wake on the next request. bochka did 26.69 runs per second at 4 vCPU / 8 GB in StarSling's public benchmark.

Can Google Agent Runtime or Unikraft Cloud run Docker?

Not inside a sandbox. Google's sandboxes run as appuser with no sudo, and Unikraft uses your Dockerfile to build the VM's filesystem without documenting a container runtime inside it. A bochka sandbox is a full Ubuntu VM with Docker, systemd and /dev/kvm ready to use.

Can I SSH into Google Agent Runtime or Unikraft Cloud?

No. Google runs each command through its execute_bash() API in a new shell, and Unikraft has announced SSH as coming soon, so today you use its sandbox plugin and CLI. You can SSH into every bochka sandbox or drive it through its API.

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. The code, shell and browser sandboxes are a separate part of the same platform called Agent Sandbox.

Where do they run?

Google runs in 23 locations across the US, Europe, Asia, Canada, Australia and Brazil, inside your own Google Cloud project. Unikraft runs in Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview