exe.dev vs Instabox
Both give each agent its own Linux virtual machine with root and Docker. exe.dev is an established service with nine regions, Docker image boot and published plans, while Instabox is a new invite-only beta with one machine size, a pause that keeps memory, and no price yet.
The companies and products
exe.dev
exe.dev, made by Bold Software, Inc., rents Linux VMs for developers and AI agents that you reach over SSH and HTTPS.
You reserve a pool of vCPUs and memory, and your VMs share it; you can also start standalone VMs billed by the second. Each VM is KVM-isolated (they use Cloud Hypervisor), boots from a container image in about two seconds, and has root, systemd and Docker. It comes with Claude Code, Codex, Pi and exe.dev's own Shelley agent, and is aimed at developers who want a persistent dev box or a sandbox for their agents.
- Company
- Bold Software, Inc.
- Preinstalled agents
- claude, codex, pi and the Shelley web agent
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. “15th cheapest of 366” means 14 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 | exe.dev: 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 A software factory clones set-up machines often: exe.dev copies a VM with cp, Instabox forks only stopped machines, and boat ranks 3rd with forks of running sandboxes. | 253rd of 367, with limits $3,701 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB exe.dev ranks 15th for always-on assistants with no session cap; Instabox has no published price to rank, and pauses a machine after 30 idle minutes unless you turn that off. | 15th cheapest of 366 $3,833 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 | 235th of 345, with limits $175 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 Handing a sandbox to each user is hard on both: exe.dev Personal stops at 50 VMs at once, and Instabox allows 5 machines per account. | 257th of 361, with limits $1,226 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 | 265th of 360, with limits $5,250 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, paused and stopped ones included, limits how many evals run side by side; exe.dev ranks 283rd and boat 10th. | 283rd of 364, with limits $1,050 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 that builds Android apps or VM images needs /dev/kvm: exe.dev offers it on Enterprise only, Instabox does not document it, and boat has it on every plan. | 288th of 377, with limits $504 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both work as a 24/7 dev box with SSH: exe.dev ranks 25th and boat 18th, while Instabox adds mosh and SSH tokens but has no price to rank. | 25th cheapest of 368 $35 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 exe.dev VMs are headless; Instabox has a Linux desktop on one template with a screenshot and click API, and boat streams a 60fps desktop. | 240th of 369, with limits $1,055 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 Instabox has an agent-browser template; on exe.dev you install and run a headless browser yourself, and boat gives a visible Chromium. | 130th of 367, with limits $530 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 | 124th of 346, with limits $278 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 | 166th of 338, with limits $5,490 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 | 60th of 360, with limits $263 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 | exe.dev | Instabox | boat |
|---|---|---|---|
| Isolation | KVM VM with Cloud Hypervisor; you can't choose the kernel | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine sizes | You size a pool that your VMs share, up to 16 vCPU on Personal; standalone VMs too | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused | Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above |
| Docker | Docker inside, with root and systemd | Docker and Docker Compose run inside | Docker and Compose run inside, with root and systemd |
| Custom images | Boot each VM from your own Docker image | Start from one of four templates or your own snapshot; no Docker images | Templates from named snapshots; no Dockerfile or OCI images |
| Nested virtualization | Enterprise only | Not documented | Yes, /dev/kvm on every plan |
| Saved state | Disk persists and is streamed to a second server; no snapshots | Up to 10 snapshots saved by hand; saving stops a running machine first, unless the server allows a live save | Disk saved every minute and on stop, plus named snapshots of running sandboxes |
| Fork | cp copies a VM's disk and config into a new VM | Fork copies a stopped machine only | Fork a running sandbox with its disk |
| Pause and resume | A stopped standalone VM keeps its disk and pays nothing for CPU and memory | Pause keeps memory and running programs; the docs say resume usually takes about a second | Stop keeps the disk and costs nothing; start boots the machine again |
| Desktop and computer use | Headless; no desktop or screen streaming | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links | 60fps Linux desktop with Chromium, computer use and browser control |
| Coding agents | Claude Code, Codex, Pi and Shelley preinstalled; only Shelley takes prompts through the API | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Seven agents preinstalled, with a prompt, steer and events API and TypeScript and Python SDKs |
| Inbound traffic | HTTPS proxy for ports 3000 to 9999, one of them public; no public IP or raw TCP | 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 per machine |
| SSH | Brokered SSH | SSH gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | SSH into every sandbox |
| Regions | 9 regions in the US, Europe, Asia and Australia | Not published | EU only: Germany, Finland, France |
| Access and price | Published plans: monthly pools plus standalone VMs billed per second | Invite-only beta; free during the beta, 5 machines per account, no published price | Published plans from $20 a month, all of it usage credit, billed per second |
Every feature Battleships tracks (43)
| Feature | exe.dev | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | 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 | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Not published | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | Yes | Not published | Yes |
| MCP server | Yes | Not published | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | Yes | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Yes | 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 | No | Not published | No |
| HIPAA | No | Not published | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither exe.dev nor Instabox is in the hpc-sandbox-benchmarks run, so there is no comparable CPU measurement for either, and this page makes no speed claim between them. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB. Instabox says a new machine's shell is ready in under a second, and exe.dev says a new VM takes about two seconds; neither has 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. exe.dev 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 | exe.dev, 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 | $35 · Personal | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $35 · Personal | 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 | $1,848 · Personal | 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 | $530 · Personal · with limits | 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 | $1,050 · Personal · with limits | No published price | $2,000 · $2000/mo · with limits |
exe.dev: Pools are reserved capacity your VMs share and bill the same whether busy or idle; a Personal 4 vCPU / 8 GiB pool is $35 a month. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour.
Instabox: Instabox is free during the beta, with 5 machines per account, and has no published price yet, so no bill can be compared with exe.dev's or boat's.
Instabox: 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.
Limits in those scenarios
exe.dev Personal allows one pool of up to 16 vCPU with 50 VMs, plus up to 50 standalone VMs, so the 300-at-once and 1,000-at-once scenarios do not fit there. Instabox allows 5 machines per account, paused and stopped ones included, 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; with no published rate, none of our scenarios can be priced on it. boat has no session cap on paid plans, but its start limits are lower than a burst of 1,000 short jobs needs.
| Scenario | exe.dev | Instabox | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use exe.dev when
you need regions outside Europe, VMs booted from your own Docker image, team SSO, or more than five machines on published plans.
- Regions around the world. Useful if your users are far from Europe: exe.dev runs in nine regions across the US, Europe, Asia and Australia.
- Your own Docker image. exe.dev boots each VM straight from your own Docker image, so your setup lives in a Dockerfile.
- Team controls and an MCP server. Its Work plan covers a whole team with SSO and roles, and it serves an MCP server for controlling VMs.
Use Instabox when
you have an invite and want to try a few 4 vCPU / 8 GiB agent machines during its free beta, with memory pause and mosh.
- Free during the beta. If you have an invite, every account can run 5 machines of 4 vCPU / 8 GiB for free while the beta lasts.
- Pause with memory. A paused machine keeps its memory and running programs, and its docs say it 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.
Where boat fits
If you are choosing between exe.dev and Instabox to run coding agents, look at boat when the agents need to branch running work, serve private URLs or be driven from your own app. boat also publishes its sizes, plans and limits today, which a beta like Instabox cannot yet.
Fork and roll back without stopping
exe.dev has no snapshots to roll back to after a bad agent step. Instabox forks only stopped machines, and saving a snapshot stops a running one first, ending its programs. boat saves every minute and forks a running sandbox.
Private URLs on 50 ports
Agents serve half-built apps and admin panels. exe.dev makes one port public and has no raw TCP; Instabox URLs are open to anyone and go offline while paused, so you add your own login. boat URLs carry a token by default.
Drive agents inside from outside
On exe.dev only Shelley takes prompts through the API, and on Instabox you run the agent yourself, so you script shell sessions with no clean way to steer a task. boat has one API to prompt, steer and stream seven agents.
Use boat when your agents need to fork running work, serve private URLs on many ports, use /dev/kvm or a 60fps desktop, and be driven from your app through one API. Compare it one to one: boat vs exe.dev and boat vs Instabox.
Questions people ask
Is exe.dev cheaper than Instabox?
It can't be compared yet. Instabox is free during its beta and publishes no price, so there is no bill to set against exe.dev's. exe.dev's Personal 4 vCPU / 8 GiB pool is $35 a month.
Which is faster, exe.dev or Instabox?
Neither has a comparable CPU measurement, so we make no speed claim. Instabox says you are in a new machine's shell in under a second, and exe.dev says a new VM takes about two seconds; neither has been measured here.
Can exe.dev and Instabox run Docker?
Yes. Both give root inside a VM and run Docker; Instabox's docs also name Docker Compose. exe.dev can also boot a VM from your own Docker image, which Instabox cannot.
Do they support nested virtualization?
exe.dev offers it on Enterprise only. Instabox does not document it. boat exposes /dev/kvm on every plan, for Android emulators and VMs.
Which one has a desktop for computer use?
Instabox has a Linux desktop with a browser on one template, with a screenshot and click API and shareable links; you bring the model. exe.dev VMs are headless. boat streams a 60fps desktop with Chromium and a computer-use agent.
Can I sign up for Instabox today?
Instabox launched on 2026-10-14 as an invite-only beta, with sign-in through GitHub or Google. exe.dev and boat both publish plans you can buy today.
Try boat
Install the CLI, then run boat new.
7-day free trial