exe.dev vs Modal VM Sandboxes
exe.dev and Modal VM Sandboxes both run each machine as a VM on Cloud Hypervisor with root, Docker and systemd. exe.dev VMs keep their disk and run until you stop them, while Modal's VMs are short-lived machines that end within 24 hours and scale to huge bursts.
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
Modal VM Sandboxes
Modal is a serverless cloud for AI work, and VM Sandboxes are the version of its sandboxes that run in a virtual machine with their own Linux kernel.
You create a VM Sandbox from Python, TypeScript or Go code with runtime="vm", run commands in it, and terminate it when the job is done. Modal built the runtime on the Rust-based Cloud Hypervisor, so Docker, FUSE, systemd and nested cgroups work, with the same API, images and prices as its gVisor sandboxes. It became generally available on 1 October 2026 and suits teams that want many short-lived agent machines next to Modal's inference and training.
- Funding
- Over $466M raised
- Generally available
- 1 October 2026; early customers launched over 20 million VMs before that
- Session length
- Default 5 minutes, maximum 24 hours
- Compliance
- SOC 2 on every plan; HIPAA on Enterprise
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 | Modal VM Sandboxes: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both run Docker in a real VM, but a Modal VM ends within 24 hours and exe.dev has no desktop or snapshots; boat fits fully with a desktop and a snapshot every minute. | 253rd of 367, with limits $3,701 a month | 84th of 367, with limits $759 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An agent that lives on its machine all month fits exe.dev, which has no session cap, while Modal VM Sandboxes stop at 24 hours; boat fits too. | 15th cheapest of 366 $3,833 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 fit Modal's model of fast starts and per-second billing; neither exe.dev nor boat is built as a code interpreter. | 235th of 345, with limits $175 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 exe.dev's Personal plan stops at 50 VMs at once, Modal's Team plan runs thousands, and boat fits with token-protected URLs and sandboxes that keep their disk. | 257th of 361, with limits $1,226 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 Huge bursts of short rollouts are what Modal is built for, while exe.dev pools bill whether jobs run or not; boat's start limits queue large bursts. | 265th of 360, with limits $5,250 a month | 171st of 360, with limits $16,322 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 | 283rd of 364, with limits $1,050 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 Both run Docker builds in a VM; boat bills per second only while jobs run and gives every plan /dev/kvm, which exe.dev keeps for Enterprise and Modal for Team on request. | 288th of 377, with limits $504 a month | 188th of 377, with limits $1,064 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB exe.dev makes a good 24/7 dev box with a disk that lasts; a Modal VM cannot stay up past a day, and boat adds a desktop in the browser. | 25th cheapest of 368 $35 a month | Can't run it | 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 Neither exe.dev nor Modal ships a desktop, so computer-use agents need you to set up a screen yourself; boat streams a 60fps desktop with Chromium. | 240th of 369, with limits $1,055 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 | 130th of 367, with limits $530 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 | 124th of 346, with limits $278 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 | 166th of 338, with limits $5,490 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 | 60th of 360, with limits $263 a month | 294th of 360, with limits $642 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 | exe.dev | Modal VM Sandboxes | boat |
|---|---|---|---|
| Isolation | KVM VM on Cloud Hypervisor, on rented servers; you can't choose the kernel | VM with its own Linux kernel on Cloud Hypervisor | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Docker, systemd, root | Yes, in every VM | Yes; start dockerd yourself as the entrypoint | Yes, in every sandbox |
| CPU benchmark (4 vCPU / 8 GB) | Not measured | 15.54 runs/s | 26.69 runs/s |
| Longest session | No cap; VMs run until you stop them | 24 hours (default 5 minutes) | No cap on paid plans; you set the time to live |
| Stop and resume | Stopped VMs keep their whole disk | No paused state; only Volumes and snapshots keep files | Stop for free, resume with the whole disk |
| Snapshots | None; the disk is streamed to a second server | Filesystem snapshots on demand; memory snapshots in alpha | Saved every minute while running and on stop; named snapshots as templates |
| Fork | cp copies a VM's disk and config into a new VM | Snapshot the filesystem into an image and boot many sandboxes from it | Fork a running sandbox with its disk |
| Desktop and computer use | Headless; no desktop or screen streaming | Not offered; an example shows how to set up Xvfb and VNC yourself | 60fps desktop, Chromium, computer-use and browser-control APIs |
| Coding agents | Claude Code, Codex, Pi and Shelley preinstalled; only Shelley takes prompts through the API | Examples only; you install the agent yourself | Seven agents preinstalled, with one API to prompt, steer and stream them |
| Secrets | Integrations inject secrets at the network edge for any HTTP host | Environment variables, or your own proxy in a sidecar | Credentials proxy for model providers and any HTTPS API you register |
| Inbound traffic | HTTPS proxy for ports 3000 to 9999, one of them public; SSH; no raw TCP | Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist | HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP |
| Outbound network rules | No egress allowlist | Block all, IP-range allowlist, domain allowlist (beta) | Open internet, no provider-side allowlist |
| Nested virtualization | Enterprise only | Team and Enterprise plans only, on request | Yes, /dev/kvm on every plan |
| Regions | 9 regions in the US, Europe, Asia and Australia | US, EU and Asia-Pacific; pinning costs 1.15x to 1.75x | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | exe.dev | Modal VM Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | Yes | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Yes | Yes |
| Desktop GUI | No | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | No | No | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | No | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | No | 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 | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Yes | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | Yes | No | Yes |
| MCP server | Yes | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | Yes | 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 | Not published | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | No | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
In the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB on 29 September 2026, boat finished 26.69 runs per second and Modal's VM runtime 15.54, so boat did about 1.7 times the CPU work. exe.dev is not in that benchmark, so there is no comparable score for it, and we don't guess one.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Modal VM Sandboxes measured on: VM Sandbox, request = size. exe.dev 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 | exe.dev, a month | Modal VM Sandboxes, 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 | $15 · Starter · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $35 · Personal | $178 · Starter · with limits | $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 | $2,229 · Starter · 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 | $530 · Personal · with limits | $792 · Team | $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 | $3,193 · Team · with limits | $2,000 · $2000/mo · with limits |
exe.dev: exe.dev sells reserved pools your VMs share: Personal is a flat monthly fee and Work is a team fee plus extra capacity by the hour, and a pool bills whether its VMs are busy or idle. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour and pay nothing for CPU and memory while stopped.
Modal VM Sandboxes: Modal bills by the second for whichever is higher, the CPU and memory you request or what you use, until the sandbox ends. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and pinning a region multiplies the price by 1.15x to 1.75x.
Modal VM Sandboxes: boat's monthly plan fee is all usage credit, and sandboxes bill per second only while they run. A stopped sandbox costs nothing and resumes with its disk.
Limits in those scenarios
A Modal VM Sandbox lives at most 24 hours and keeps only what is in a Volume or snapshot, so the workday, always-on and 50-agent scenarios don't fit there, and the 1,000-job burst on Team runs on shared vCPUs. exe.dev Personal stops at 50 VMs at once, so the 300-at-once and 1,000-at-once scenarios don't fit, and its pools bill whether used or not. On boat, start-rate limits mean even the top plan queues 1,000 short jobs at once.
| Scenario | exe.dev | Modal VM Sandboxes | 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 | None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use exe.dev when
you want a lasting VM or a team pool in regions around the world, booted from your own Docker image, with SSO and an MCP server.
- A machine that stays. For a long-lived dev box or agent home: exe.dev VMs keep their disk and run until you stop them.
- Agents and MCP ready. Claude Code, Codex, Pi and Shelley come preinstalled, and an MCP server lets tools like Claude Code control your VMs.
- One team fee. The Work plan covers a whole team with unlimited users, SSO and roles, with VMs in any of nine regions.
Use Modal VM Sandboxes when
you run huge bursts of short jobs that end within a day, need strict outbound rules, or already run your models on Modal.
- Very large bursts. Useful for huge bursts of short jobs: Modal runs 5,000 containers at once on Team.
- Strict outbound rules. Modal can block a sandbox's outbound traffic or allow only chosen IP ranges or domains.
- Next to your models. Useful if you already serve or train models on Modal: sandboxes and GPUs sit on one account and one bill.
Where boat fits
If your agents work for hours in a machine they come back to, boat gives them a full VM that keeps its disk like exe.dev, plus a desktop, a snapshot every minute and one API to drive agents inside from outside. It also did about 1.7 times the CPU work of Modal's VM runtime in the same benchmark run.
A screen for your agents
exe.dev VMs are headless and Modal VM Sandboxes have no desktop, so a computer-use agent has nothing to look at. On Modal you install Xvfb, VNC and a browser yourself. boat streams a 60fps desktop with Chromium.
Work that is never lost
exe.dev has no snapshots, so one bad agent step can wreck a whole session. A Modal VM ends within 24 hours and keeps only files in a Volume or snapshot you wrote code for. boat saves every minute and never cuts sessions off.
Agents driven from outside
On exe.dev only Shelley takes prompts through the API, and on Modal you install the agent yourself and keep keys in environment variables. boat ships seven agents behind one API, with a credentials proxy that keeps real keys out.
Use boat when your agents work for hours or days in a machine they come back to, with a desktop, a snapshot every minute, /dev/kvm and one API to drive agents inside from outside. Compare it one to one: boat vs exe.dev and boat vs Modal VM Sandboxes.
Questions people ask
Is exe.dev cheaper than Modal VM Sandboxes?
It depends on the workload. One agent running all month costs $35 on exe.dev against $178 on Modal, and 50 parallel agents cost $1,848 against $2,229. For one agent on workdays Modal is $15 against $35, but its files reset between days unless you use a Volume. boat costs $26 a month for the always-on agent and $317 for the fleet.
Which is faster, exe.dev or Modal VM Sandboxes?
Modal's VM runtime scored 15.54 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and exe.dev has not been measured, so we can't compare the two. boat scored 26.69 in the same run.
Can exe.dev and Modal VM Sandboxes run Docker?
Yes. Both are real VMs with root and systemd, so Docker runs inside. On Modal you start dockerd yourself as the entrypoint. Nested virtualization is Enterprise only on exe.dev and Team or Enterprise on request on Modal, while boat has /dev/kvm on every plan.
How long can a session run on each?
exe.dev has no session cap: a VM runs until you stop or delete it. A Modal VM Sandbox defaults to 5 minutes and stops at 24 hours at most; for longer work Modal suggests a filesystem snapshot and a new sandbox. boat has no session cap on paid plans.
Do exe.dev or Modal VM Sandboxes have GPUs?
No. exe.dev VMs have no GPUs, and Modal's GPU sandboxes need its gVisor runtime, not the VM runtime. boat has no GPUs either.
Try boat
Install the CLI, then run boat new.
7-day free trial