Google Agent Runtime vs Instabox
Google Agent Runtime hosts your agent code on Google Cloud and runs its code in locked containers with no root, no Docker and no SSH. Instabox, an invite-only beta that launched today, gives each agent a Firecracker microVM with root, Docker and SSH, in one size and free for now.
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.
Instabox
Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.
Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.
- Isolation
- Firecracker microVM per machine
- Machines per account
- 5, in any state: paused and stopped ones count
- Company
- InsForge AI, Inc.
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 | Instabox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Google's sandboxes have no root or Docker, and Instabox has Docker but one 4 vCPU / 8 GiB size and forks only stopped machines; boat forks running sandboxes and goes up to 16 vCPU / 32 GB. | 295th of 367, with limits $5,801 a month | No published price | 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 Instabox documents no maximum run time but pauses after 30 idle minutes unless you turn that off. | 28th cheapest of 366 $7,519 a month | No published price | 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 This is where Google fits best: its Code Execution sandbox is a ready Python interpreter, while an Instabox API exec call runs at most 10 minutes, with 4 at once. | 254th of 345, with limits $275 a month | No published price | 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 Instabox allows 5 machines per account, paused and stopped ones included, so it cannot give a sandbox to each of many users; Google can, but gives your users no public URL. | 280th of 361, with limits $1,916 a month | No published price | 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 | No published price | 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 Instabox's 5-machine cap limits how many evals run at once, and Google's sandboxes are billed for as long as they exist. | 79th cheapest of 364 $2,060 a month | No published price | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build containers need Docker, which Instabox and boat run and Google's unprivileged sandboxes do not; Instabox does not document /dev/kvm, which boat exposes. | 98th cheapest of 377 $989 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Google has no SSH into a sandbox, so it does not work as a dev box; Instabox adds an SSH gateway with mosh, and boat gives you SSH, a desktop and published plans. | 311th of 368, with limits $241 a month | No published price | 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 you a browser in a container with a VNC view, Instabox a Linux desktop with a browser on one template, and boat a full 60fps desktop with Chromium. | 283rd of 369, with limits $1,648 a month | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | Can't run it |
Key features
| Feature | Google Agent Runtime | Instabox | boat |
|---|---|---|---|
| Isolation | Secure container sandboxing inside your Google Cloud project | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root, Docker and nested virtualization | Runs as appuser with no sudo; images must not need root; no Docker or /dev/kvm | Root, Docker and Docker Compose inside; nested virtualization: Not documented | Root, systemd, Docker and /dev/kvm on every machine |
| Machine size | Runtime: 1 to 8 vCPU and up to 32 GiB; sandbox maximum not published | One size: 4 vCPU / 8 GiB with 20 GB storage; 5 machines per account, in any state | Up to 8 vCPU / 16 GB on the $20 plan, 16 vCPU / 32 GB from the $100 plan |
| Shell access | execute_bash() API calls; each command runs in a new shell; no SSH | SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | SSH, plus an API for commands |
| Pause and resume | Pause keeps the file system and costs less, at a rate Google does not publish | Pause keeps memory and running programs; resume usually takes about a second | Stop keeps the disk and costs nothing; start boots the machine again |
| Snapshots and branching | Snapshots keep memory and files; start many sandboxes from one snapshot | Up to 10 snapshots, saved by hand; fork copies a stopped machine only | Disk saved every minute and on stop; fork a running sandbox (no memory snapshots) |
| How long a machine lives | TTL of up to 7 days for a custom container and 14 days for Code Execution | No maximum run time documented; pauses after 30 idle minutes unless you change it | No session cap on paid plans |
| Reaching what the agent serves | Through Google's API, or a private endpoint in your own VPC; no public URL documented | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS on up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| Outbound internet | Off unless the template turns it on; can route through your VPC with Cloud NAT, a static IP or a firewall | Not documented | Open internet on every plan; no provider-side allowlist |
| Desktop and computer use | A browser in a container with a VNC live view, a click, type and screenshot API, and CDP | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links | 60fps Linux desktop with Chromium and a computer-use agent, embeddable stream |
| Coding agents | Managed Agents API (Preview) runs Google's Antigravity harness | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | You provision and scope the credentials the agent uses | Vault writes your secrets into each machine as environment variables or files | Credentials proxy: real keys never enter the sandbox, for model providers and any HTTPS API |
| Hosting your agent code | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | You run your own agent inside a machine | You run your own agent loop inside a sandbox |
| Regions | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | Not published | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Google Agent Runtime | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | No | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | No | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | No | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | 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 | No | No |
| HTTPS preview URLs | No | Yes | Yes |
| Raw TCP inbound | Not published | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Not published | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | Yes | Not published | Yes |
| MCP server | No | Not published | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | Yes | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | No | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | Yes | Not published | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Google Agent Runtime or for Instabox, so this page makes no speed claim between them. In StarSling's public run of 2026-09-29, boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Instabox says a new machine's shell is ready in under a second; that has not been measured here.
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 Instabox 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 | Instabox, 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 | No published price | $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 | No published price | $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 | No published price | $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 | No published price | $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 | No published price | $2,000 · $2000/mo · with limits |
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour for what you allocate, with the first 50 vCPU-hours and 100 GiB-hours free each month. Runtime skips idle time between turns, but sandboxes are billed while they exist, and disk and egress rates are not published.
Instabox: Instabox is free during the beta, with 5 machines per user, and publishes no price yet ("Free until we figure it out"). No bill can be compared with Google's until it does.
Instabox: 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
Instabox allows 5 machines per account, paused and stopped ones included, and publishes no rate, so none of the five scenarios can be priced or run there at scale today. On Google, the 50-agent fleet does not fit because its sandboxes have no Docker, a sandbox is deleted when its TTL ends, and disk and egress stay unpriced. On boat the 1,000-job burst is the problem: the $2,000 plan caps starts per hour and per day, so the jobs get queued.
| Scenario | Google Agent Runtime | Instabox | 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 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 your agents must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
- Memory snapshots and regions worldwide. Useful if you branch a sandbox with its memory, or need to run in the US or Asia: Google offers 23 locations.
Use Instabox when
you want to try a few free 4 vCPU / 8 GiB microVMs with root, Docker, memory pause and mosh during its invite-only beta.
- A real VM with root and Docker. Useful if your agent needs sudo or Docker Compose: each Instabox machine is a microVM with its own kernel and root.
- Pause with memory, SSH with mosh. Useful for a cloud dev box: a paused machine keeps its running programs, and its SSH gateway relays mosh.
- Free during the beta. Useful for trying things out: each account gets 5 machines of 4 vCPU / 8 GiB for free, with no later price published.
Where boat fits
Look at boat if your agents need a real computer with room to grow: root, Docker and /dev/kvm on a full VM, sizes up to 16 vCPU / 32 GB, and no cap of 5 machines. boat forks running sandboxes, keeps port URLs private by default, and has Claude Code, Codex and other coding agents built in, on plans that are published today.
Root, Docker and /dev/kvm on every machine
On Google an agent runs as appuser with no sudo, so you bake tools into an image and run Docker somewhere else. Instabox has Docker, but one 4 vCPU / 8 GiB size and no documented /dev/kvm for emulators.
Branch work without stopping it
Instabox forks only a stopped machine, which ends its running programs, and a Google sandbox is deleted when its TTL ends. boat forks a running sandbox, saves its disk every minute and has no session cap on paid plans.
Private URLs for what agents build
Google describes no public URL, so a preview needs your own VPC endpoint, load balancer or tunnel. Instabox URLs are open to anyone who finds them. boat serves HTTPS on up to 50 ports with a token by default, plus raw TCP.
Use boat when your agents need a full VM with root, Docker and /dev/kvm, bigger sizes, forks of running work and private port URLs, with coding agents built in and terms published today. Compare it one to one: boat vs Google Agent Runtime and boat vs Instabox.
Questions people ask
Is Google Agent Runtime cheaper than Instabox?
It can't be compared yet. Instabox is free during the beta and publishes no price, so there is no bill to set against Google's. For one coding agent on workdays, Google comes to $73 a month and boat to $20.
Which is faster, Google Agent Runtime or Instabox?
Neither has a comparable CPU measurement, so we make no speed claim. Instabox says a new machine's shell is ready in under a second, and its docs say a paused machine usually resumes in about a second; neither has been measured here. boat did 26.69 runs per second in StarSling's benchmark.
Can Google Agent Runtime run Docker?
No. Its shell sandbox runs commands as the unprivileged user appuser with no sudo, and custom images must not need root. Instabox runs Docker and Docker Compose inside its microVMs, and boat runs Docker, systemd and /dev/kvm on every VM.
Can I SSH into Google Agent Runtime or Instabox?
Not into Google's sandboxes: you send commands through the execute_bash() API, and each one runs in a new shell. Instabox gives you SSH through a gateway, with mosh and paste-anywhere SSH tokens. boat gives you SSH into every sandbox.
Can anyone sign up for Instabox?
Not yet. It launched on 2026-10-14 as an invite-only beta, with sign-in through GitHub or Google. Each account gets 5 free machines of 4 vCPU / 8 GiB, and paused and stopped ones count.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Google Agent Runtime
- boat vs Instabox
- 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