Morph Cloud vs Google Agent Runtime
Morph Cloud sells full virtual machines with root and Docker that can pause, branch and wake with their memory. 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
Morph Cloud
Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.
You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state, and it also sells managed GitHub Actions runners and a shared filesystem.
- Regions
- Not published
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. “16th cheapest of 345” means 15 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 | Morph Cloud: price rank | Google Agent Runtime: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Morph runs Docker and full builds on a real VM, while Google's sandboxes have no root or Docker; bochka adds coding agents you prompt and steer by API. | 198th of 367, with limits $2,288 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 hosts agent code and skips billing between turns, but a sandbox is deleted when its TTL ends; Morph and bochka keep a machine running with no session cap. | 235th of 366, with limits $3,014 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 Both fit short code runs: Morph pauses a machine with its memory and wakes it on the next request, and Google has a ready Python interpreter sandbox. | 16th cheapest of 345 $154 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 Morph gives each user a VM with named HTTP services, while Google reaches sandboxes only through its API or your VPC; bochka serves HTTPS on up to 50 ports. | 12th cheapest of 361 $905 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 Both can start many copies from one memory snapshot; Morph branches a running VM in under 250 ms. | 86th of 360, with limits $4,847 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 | 38th cheapest of 364 $675 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 Morph sells managed GitHub Actions runners, and Google's sandboxes cannot build containers without Docker; bochka runs your own runner with Docker and systemd. | 39th cheapest of 377 $355 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 Morph gives you SSH into a VM, while Google has no SSH and runs each command in a new shell; bochka adds a 60fps desktop. | 85th cheapest of 368 $116 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 click and type API, Morph has you install the browser and agent yourself, and bochka streams a full 60fps desktop with Chromium. | 182nd of 369, with limits $595 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 | 214th of 367, with limits $250 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 | 239th of 346, with limits $234 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 | 154th of 338, with limits $4,750 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 | 214th of 360, with limits $228 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 | Morph Cloud | Google Agent Runtime | bochka |
|---|---|---|---|
| Isolation | Full VM with its own kernel | Secure container sandboxing inside your Google Cloud project | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root and Docker | Yes, including Docker in Docker and local Kubernetes | Runs as appuser with no sudo; images must not need root; no Docker documented | Root, systemd and Docker on every machine |
| Nested virtualization | Experimental | No /dev/kvm documented | Yes, /dev/kvm for Android emulators and VMs |
| Shell access | SSH through Morph's gateway | execute_bash() API calls; each command runs in a new shell; no SSH | SSH, plus an API for commands |
| Memory snapshots and branching | Snapshot and branch a running VM with its memory in under 250 ms | Snapshots keep memory and files; start many sandboxes from one snapshot | Fork a running sandbox with its disk; resume reboots from disk |
| Pause and wake | A paused VM bills only its snapshot and wakes on the next HTTP request, SSH or exec call | Pause keeps the file system and costs less, at a rate not published | Disk saved every minute and on every stop; a stopped sandbox is free and starts by API |
| How long a machine lives | No expiry unless you set a TTL | TTL of up to 7 days for a custom container and 14 days for Code Execution | No session cap on paid plans |
| Desktop and computer use | Browser-based remote desktop; you install the browser and any computer use agent | A browser in a container with a VNC view, a click, type and screenshot API, and CDP | 60fps Linux desktop with Chromium and a computer use API, embeddable in your app |
| Coding agents | You install the agent and drive it through a tmux API | Managed Agents API (Preview) runs Google's Antigravity harness | Seven agents preinstalled, including Claude Code and Codex, with a prompt, steer and events API |
| Keeping keys out of the sandbox | Responses Proxy for model APIs; other secrets go into the machine | You provision and scope the credentials the agent uses | Credentials proxy for model providers and any HTTPS API; switch to another account when credits run out |
| Reaching the machine from outside | Named HTTP services with optional API key auth; no raw TCP | Through Google's API or a private endpoint in your VPC; no public URL documented | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP |
| Outbound network control | Open internet | Off unless the template turns it on; route through your VPC with Cloud NAT, a static IP or Cloud NGFW | Open internet on every plan |
| Hosting agent code | You run your own loop on a VM | Deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | You run your own loop inside a sandbox |
| Guest systems and regions | Linux, with experimental Windows and macOS (x86); regions not published | Linux; 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | Linux; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Morph Cloud | Google Agent Runtime | bochka |
|---|---|---|---|
| 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 | Yes | 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 | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | No | No | No |
| GPU | No | No | No |
| Windows | Yes | 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) | Yes | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Not published | Yes | No |
| SOC 2 | Not published | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | Not published | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Morph Cloud or Google Agent Runtime: neither is in StarSling's hpc-sandbox-benchmarks run. In that run of 2026-09-29, bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Morph's under 250 ms snapshot restore 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. Morph Cloud and Google Agent Runtime 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 | Morph Cloud, a month | Google Agent Runtime, 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 | $32 · Developer | $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 | $121 · Team | $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 | $1,459 · Scale | $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 | $325 · Scale | $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 | $869 · Scale | $2,060 · Pay as you go | $2,000 · $2000/mo · with limits |
Morph Cloud: Morph bills MCUs at $0.05 each: per hour, a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. Team ($40 a month) and Scale ($250 a month) are prepaid MCU bundles at a discount, and a paused VM bills only its snapshot.
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 and egress rates are not published.
Google Agent Runtime: Plans start at $20 a month, and the whole fee is usage credit spent per second while a sandbox runs. 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 inside, and a sandbox is deleted when its TTL ends, 7 days at most for a custom container. Morph fits every scenario, but its limits are account-wide pools: the Developer pool of 64 vCPU holds only 16 machines at 4 vCPU, and disk above 16 GiB per MCU raises the bill. Neither publishes egress prices. bochka's limit is starts: for 1,000 short jobs at once, the $2,000 plan queues them.
| Scenario | Morph Cloud | Google Agent Runtime | 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 Morph Cloud when
your agents need a full VM with root and Docker, and branch from one running state with its memory or sleep and wake on demand.
- A real VM with root and Docker. For agents that need sudo, Docker or Kubernetes: every Morph instance is a full VM, which Google's locked sandboxes are not.
- Branch and wake with memory. For agents that fan out from one running state or sleep between requests: Morph branches in under 250 ms and wakes on demand.
- Managed CI runners and more guest systems. For teams that also want GitHub Actions runners, or experimental Windows and macOS (x86) guests, from the same balance.
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.
- A managed home for agent code. For teams building with ADK or LangGraph: Agent Runtime hosts the agent and does not bill 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 and a ready browser. For agents that must run in the US or Asia, or need a browser with a click and type API out of the box.
Where bochka fits
If your agents need a real computer, Morph gets closer than Google, but you still build the agent harness, the desktop and the key handling yourself. bochka gives every agent a full VM with root, Docker and /dev/kvm, plus coding agents, a 60fps desktop and a credentials proxy already inside.
Coding agents you drive from outside
On Morph you install Claude Code or Codex and drive it by sending keystrokes to tmux and reading the screen. Google runs only its own Antigravity harness. bochka ships seven agents with a prompt, steer and events API.
Real keys stay outside the machine
Morph's proxy covers model APIs only, and on Google you pass credentials in yourself, so keys for GitHub or Stripe sit where a prompt injection can read them. bochka's proxy covers any HTTPS API.
A desktop and public URLs, ready
Google gives a browser only and no public URL, and Morph has you build the desktop and browser yourself. bochka streams a 60fps desktop with Chromium and serves HTTPS on up to 50 ports, plus raw TCP.
Use bochka when your agents need a real computer that arrives ready: root, Docker and /dev/kvm, coding agents you steer by API, a 60fps desktop, keys kept outside and HTTPS on many ports in the EU. Compare it one to one: bochka vs Morph Cloud and bochka vs Google Agent Runtime.
Questions people ask
Is Morph Cloud cheaper than Google Agent Runtime?
In all five scenarios we priced, yes: one agent running all month is $121 on Morph and $301 on Google, and 1,000 short jobs at once are $869 versus $2,060. bochka comes to $26 a month for the always-on agent. Google's numbers assume a sandbox that exists all those hours; a Runtime agent idle between turns bills less.
Which is faster?
Neither Morph Cloud nor Google Agent Runtime has a comparable CPU measurement. bochka did 26.69 runs per second on StarSling's Node.js build-and-test loop at 4 vCPU / 8 GB.
Can Morph Cloud and Google Agent Runtime run Docker?
Morph can: every instance is a full VM with root, Docker and local Kubernetes. Google's sandboxes run as the unprivileged user appuser with no sudo, so Docker is not available. bochka runs root, Docker and /dev/kvm on every VM.
Can both branch a sandbox with its memory?
Yes. Morph branches a running VM with its memory in under 250 ms, and Google can start many sandboxes from one snapshot that keeps memory and files. bochka forks a running sandbox with its disk, so the copy boots fresh.
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.
Can I run Claude Code on Morph Cloud or Google Agent Runtime?
On Morph you install it in a Devbox and drive it through a tmux API. Google names only its own Antigravity harness, so you would bake Claude Code into an image and pass keys in. On bochka it comes preinstalled with a prompt, steer and events API.
Try bochka
Install the CLI, then run bochka new.
Product preview