boat vs Instabox
Both give each agent its own Linux virtual machine with root and Docker. Instabox is a new free beta with one machine size, while boat forks running sandboxes, keeps its port URLs private by default and publishes its sizes, regions and limits.
Where boat stands out
Fork and snapshot without stopping
boat forks a running sandbox into a new one, and it saves the disk every minute on its own. On Instabox, a fork copies a stopped machine, and saving a snapshot stops a running machine first unless the server allows a live save.
Port URLs that are private by default
A new boat port URL carries a token, so only people you give it to can open it, and you can host up to 50 ports plus raw TCP. Instabox's docs say a published port URL is not a secret: anyone can reach the whole service until you unpublish it.
Sizes and terms you can plan around
boat offers several machine sizes up to 16 vCPU / 32 GB, publishes its plans, start limits and EU regions, and has a measured CPU score of 26.69 runs per second. Instabox has one 4 vCPU / 8 GiB size, 5 machines per account, and no published price, regions or terms yet.
The companies and products
boat
boat.dev runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.
You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
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. “3rd cheapest of 367” means 2 of the other 366 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 | boat: price rank | Instabox: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory clones a set-up machine often: Instabox forks only stopped machines, while boat forks a running sandbox and goes up to 16 vCPU / 32 GB. | 3rd cheapest of 367 $634 a month | No published price |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both can keep a machine running with no session cap; Instabox pauses a machine after 30 idle minutes unless you turn that off. | 5th cheapest of 366 $657 a month | No published price |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 186th of 345, with limits $2,000 a month | No published price |
| 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 yet give a sandbox to each of many users. | Cheapest of 361 $209 a month | No published price |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 34th of 360, with limits $2,000 a month | No published price |
| 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 the same time. | 10th cheapest of 364 $200 a month | No published price |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI runners that build Android apps or VM images need /dev/kvm, which boat exposes and Instabox does not document. | 4th cheapest of 377 $86 a month | No published price |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both work as a cloud dev box with SSH; Instabox adds mosh and paste-anywhere SSH tokens, and boat adds a published price and plans. | 18th cheapest of 368 $26 a month | No published price |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Both have a Linux desktop with a browser and screenshot and click control; boat streams it at 60fps, and Instabox can share a view or control link. | 6th cheapest of 369 $200 a month | No published price |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 7th cheapest of 367 $200 a month | No published price |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 6th cheapest of 346 $90 a month | No published price |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 71st of 338, with limits $1,800 a month | No published price |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 2nd cheapest of 360 $200 a month | No published price |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Can't run it | No published price |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | No published price |
Key features
| Feature | boat | Instabox |
|---|---|---|
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Firecracker microVM with its own kernel and root |
| Machine sizes | Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused |
| CPU benchmark (4 vCPU / 8 GB) | 26.69 runs/s | Not measured |
| Docker | Docker and Compose run inside, with root and systemd | Docker and Docker Compose run inside |
| Nested virtualization | Yes, /dev/kvm for Android emulators and VMs | Not offered in the docs |
| Fork | Fork a running sandbox with its disk | Fork copies a stopped machine only |
| Snapshots | Disk saved every minute and on stop, plus named snapshots of running sandboxes | Saved by hand, up to 10; saving stops a running machine first, unless the server allows a live save |
| Pause and resume | Stop keeps the disk; start boots the machine again | Pause keeps memory and running programs; resume usually takes about a second |
| Public port URLs | HTTPS on up to 50 ports, token-protected by default; raw TCP too | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused |
| SSH | SSH into every sandbox | SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh |
| Desktop and computer use | 60fps Linux desktop with Chromium and a computer-use agent | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model |
| Coding agents | Seven agents preinstalled, with a prompt, steer and events API | Templates and saved agent sign-ins in snapshots; you run the agent yourself |
| Keeping API keys out of the sandbox | Credentials proxy: real keys never enter the sandbox, for model providers and any HTTPS API | Vault writes your secrets into each machine as environment variables or files |
| Regions | EU only (Germany, Finland, France) | Not published |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | Not published |
Every feature Battleships tracks (43)
| Feature | boat | Instabox |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | Not published |
| Root | Yes | Yes |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | Yes |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | No |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | Yes |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No | No |
| Egress allowlist | No | Not published |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | Not published |
| Agent harness API | Yes | Not published |
| MCP server | No | Not published |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | Not published |
| Self-hosting | No | Not published |
| BYOC | No | Not published |
| Open source | No | No |
| Scoped API keys | Yes | Yes |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | Yes |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | Not published |
| HIPAA | No | Not published |
| EU data residency | Yes | Not published |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement for Instabox: its CPU speed has not been benchmarked, so this page makes no speed claim either way. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB. Instabox says a new machine's shell is ready in under a second; that has not been measured either.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Instabox 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 | boat, a month | Instabox, 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 | $20 · $20/mo | No published price |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | No published price |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $317 · $20/mo × 3 seats | No published price |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $200 · $100/mo × 2 seats | No published price |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $2,000 · $2000/mo · with limits | No published price |
boat: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Instabox: Instabox is free during the beta and has no published price yet, so a bill can't be compared.
Limits in those scenarios
Instabox allows 5 machines per account, and paused and stopped ones count, so the 50-agent and user-sandbox scenarios do not fit it today. Every machine is 4 vCPU / 8 GiB with 20 GB storage, and an API exec call runs at most 10 minutes, with 4 at once. boat has no session cap on paid plans, but its start limits are lower than a burst of 1,000 short jobs needs: the $2,000 plan caps starts per hour and per day.
| Scenario | boat | Instabox |
|---|---|---|
| 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 Instabox when
you want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with memory pause and mosh.
- Free during the beta. During the beta, every account can run 5 machines of 4 vCPU / 8 GiB for free.
- Pause with memory. A paused machine keeps its memory and running programs and usually resumes in about a second.
- SSH gateway with mosh. Its SSH gateway relays mosh and gives paste-anywhere SSH tokens, so a session survives sleep and network changes.
Use boat when
your agents need to fork running work, serve private URLs, pick a bigger machine or run more than five at once, on terms that are published today.
- Fork and snapshot without stopping. An agent that wants to branch its work in the middle of a task has to stop on Instabox, which ends its running programs. On boat the original keeps working while the copy starts.
- Port URLs that are private by default. Agents often serve half-built apps, admin panels and databases. On Instabox anyone who finds the URL can reach them, so you have to add your own login in front of each service.
- Sizes and terms you can plan around. A build that needs more memory, or a fleet of more than five agents, does not fit Instabox today. Without published terms you also cannot know what the same work will cost after the beta.
Questions people ask
Is boat cheaper than Instabox?
It can't be compared yet. Instabox is free during the beta and has no published price, so there is no bill to set against boat's. boat's prices for each scenario are in the table above.
Is Instabox free?
Yes, for now. Its pricing page says it is free until they figure out pricing, with 5 machines of 4 vCPU and 8 GB for everyone. No end date or later price is published.
Does Instabox start a machine in under a second?
Instabox says you are in a new machine's shell in under a second. Its docs say a paused machine usually resumes in about a second. Neither has been measured here.
Can I fork a running machine on Instabox?
No. Instabox's fork copies a stopped machine, and saving a snapshot stops a running machine first unless the server allows a live save. boat forks a running sandbox and keeps the original working.
Are Instabox port URLs private?
No. Its docs say a published URL is not a secret and anyone can reach the service until you unpublish it. boat's port URLs carry a token by default, and you can make one public if you want.
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.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- boat vs Blaxel
- boat vs Runloop
- boat vs Tensorlake
- boat vs Cloudflare Sandbox
- boat vs exe.dev
- boat vs Agent 37
- boat vs Oracle Cloud
- boat vs IONOS Cloud
- E2B vs Instabox
- Daytona vs Instabox
- Modal vs Instabox
- Vercel Sandbox vs Instabox
- Cloudflare Sandbox vs Instabox
- Blaxel vs Instabox
- Runloop vs Instabox
- Tensorlake vs Instabox