exe.dev vs Agent 37
exe.dev gives every machine a full KVM VM with root, systemd and Docker, billed from a reserved pool, in nine regions. Agent 37 starts with lighter gVisor sandboxes in the US that sleep when idle, keep their memory and bill per minute from a wallet.
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
Agent 37
Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.
You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor; a VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.
- Where it runs
- Dedicated servers in the United States
- Instance types
- Default (shared), Performance (dedicated cores), VM
- Compliance
- SOC 2 Type I, Type II in progress
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 | Agent 37: 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 needs Docker on every machine: exe.dev has it in every VM, Agent 37 only on its VM type at 2.5 times the compute rate, and boat in every sandbox with a desktop too. | 253rd of 367, with limits $3,701 a month | 2nd cheapest of 367 $551 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 ranks first for always-on assistants because its instances sleep with their memory kept; exe.dev and boat both fit too, with a VM that runs until you stop it. | 15th cheapest of 366 $3,833 a month | Cheapest of 366 $279 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 Agent 37's small default sandboxes suit short code runs; exe.dev and boat are built for longer sessions and rank low here. | 235th of 345, with limits $175 a month | Cheapest of 345 $22 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 For sandboxes you hand to users, exe.dev Personal stops at 50 VMs at once and Agent 37 at 200 instances counting sleeping ones; boat plans go up to 2,000 at once. | 257th of 361, with limits $1,226 a month | 30th of 361, with limits $79 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 | 265th of 360, with limits $5,250 a month | 6th of 360, with limits $363 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 | 90th of 364, with limits $58 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 Agent 37's per-minute wallet suits CI runs, while exe.dev pools bill whether jobs run or not; boat bills per second only while a sandbox runs. | 288th of 377, with limits $504 a month | 2nd cheapest of 377 $84 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB All three make good 24/7 dev boxes; Agent 37 is cheapest to keep around, exe.dev offers nine regions, and boat adds a desktop in the browser. | 25th cheapest of 368 $35 a month | 3rd cheapest of 368 $12 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 Computer-use agents need a screen: exe.dev VMs are headless, Agent 37 adds a noVNC desktop through a template, and boat streams a 60fps desktop out of the box. | 240th of 369, with limits $1,055 a month | Cheapest of 369 $53 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 | 130th of 367, with limits $530 a month | 48th of 367, with limits $29 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 | 124th of 346, with limits $278 a month | Cheapest of 346 $32 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 | 166th of 338, with limits $5,490 a month | 36th of 338, with limits $648 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 Agent 37 is the lowest-cost fit for many parallel attempts, and boat can fork one running attempt into many; exe.dev's cp copies a VM into a new one. | 60th of 360, with limits $263 a month | Cheapest of 360 $43 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 | Agent 37 | boat |
|---|---|---|---|
| Isolation | KVM VM with Cloud Hypervisor on rented bare metal; you can't choose the kernel | gVisor by default; full VM with its own kernel as an opt-in instance type | Every sandbox is a full VM with its own kernel, on dedicated AMD Ryzen 9 9950X hosts |
| Docker inside | Yes, in every VM | Only on the VM type, at 2.5x the default compute rate; the default gVisor type cannot run a Docker daemon | Yes, in every sandbox |
| systemd and init | Root and systemd in every VM | Your entrypoint is PID 1 with no init system, even on the VM type | systemd runs as in any Linux server |
| Nested virtualization | Enterprise only | /dev/kvm on the VM type, with a ready Android template | /dev/kvm in every sandbox, on every plan |
| Sleep when idle | No idle sleep; VMs run until you stop them | Opt-in auto-sleep after a quiet period, memory checkpointed, wakes on the next request | No idle timer; a time limit you set, or no limit; a stopped sandbox keeps its disk and reboots on resume |
| Saved state and forks | Disk streamed to a second server; cp copies a VM into a new one; no snapshots | No fork; daily backups plus one on-demand backup, restored in place only | Snapshots every minute and on stop; fork a running sandbox; named snapshots as shareable templates |
| Custom images | Boot from your own Docker image | Your own linux/amd64 Docker image as a template | Templates from named snapshots; no Dockerfile or OCI images |
| Built-in agents | Claude Code, Codex, Pi and Shelley; only Shelley takes prompts through the API | Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API per instance | Claude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code, Mistral Vibe, with one API to prompt, steer and stream events |
| Keys kept out of the sandbox | Integrations inject secrets at the network edge for any HTTP host, S3 and GitHub | Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars | Credentials proxy for model providers and any HTTPS API you register; switch to another account when one runs out of credits |
| Desktop and computer use | Headless; no desktop or screen streaming | noVNC desktop through a template build or the Ubuntu VM template | 60fps desktop and Chromium in every sandbox, computer use, embeddable stream |
| Inbound traffic | HTTPS proxy for ports 3000 to 9999, one of them public; brokered SSH; no public IP or raw TCP | HTTPS URL per port, signed URLs, custom domains; no public IP; SSH through a WebSocket tunnel | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 per machine |
| Regions | 9 regions in the US, Europe, Asia and Australia | Dedicated servers in the United States | EU only: Germany, Finland, France, with EU data residency |
| Billing | Reserved pools billed whether used or not, plus standalone VMs billed per second | Prepaid wallet metered per minute, no plan fee or seat charge | Monthly plan that is all usage credit, billed per second while a sandbox runs |
| How many at once | Personal: one pool of up to 50 VMs, plus up to 50 standalone VMs | 1 to 200 instances by lifetime top-ups, counting sleeping and stopped ones | 100 to 2,000 at once by plan, with a cap on starts per hour and per day |
Every feature Battleships tracks (43)
| Feature | exe.dev | Agent 37 | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | Yes | No | 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 | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | 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 | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | No | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | 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 | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | No | Yes | No |
| HIPAA | No | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither exe.dev nor Agent 37 is in the hpc-sandbox-benchmarks run, so there is no comparable CPU measurement for them. boat scored 26.69 runs/s on that Node.js build-and-test loop at 4 vCPU / 8 GB. Agent 37 says its default instances share host resources, and sells a Performance type on dedicated cores.
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 Agent 37 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 | Agent 37, 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 | $6 · Wallet (any top-up) | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $35 · Personal | $12 · Wallet (any top-up) | $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 | $329 · Wallet ($100 lifetime top-ups) | $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 | $33 · Wallet ($250 lifetime top-ups) · with limits | $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 | $73 · Wallet ($250 lifetime top-ups) · with limits | $2,000 · $2000/mo · with limits |
exe.dev: Personal is a flat monthly pool your VMs share, from $15 for 2 vCPU / 4 GB to $35 for 4 vCPU / 8 GB, billed whether used or not. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour.
Agent 37: A prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while asleep. VM compute costs 2.5x and Performance 4x the default rate.
Agent 37: A monthly plan from $20, all of it usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
exe.dev Personal allows up to 50 VMs at once, and Agent 37 stops at 200 instances counting sleeping and stopped ones, so neither fits 300 user sandboxes or 1,000 short jobs at once. boat fits the 300, but its start limits stop it in the 1,000-at-once burst too. Agent 37's 4 vCPU / 8 GB instance takes at most 20 GB of disk, and its 50-agent price uses the VM type because that scenario needs Docker. exe.dev pools bill the same whether VMs are busy or idle.
| Scenario | exe.dev | Agent 37 | 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 want full VMs with Docker and systemd close to users outside the EU, booted from your own Docker image, with SSO and roles for your team.
- A full VM with Docker and systemd. Every exe.dev machine is a KVM VM with root, systemd and Docker, so services and containers run as on a normal server.
- Regions around the world. Useful if your users are far from the US: exe.dev runs in nine regions across the US, Europe, Asia and Australia.
- 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 Agent 37 when
you host one mostly idle assistant per customer in the US that should sleep with its memory kept, and you want to pay per minute.
- Sleeps when idle and keeps its memory. Useful for assistants that sit idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
- Pay per minute from a wallet. No plan fee or reserved pool: you top up a wallet and pay per minute only for what runs and the disk you keep.
- Agent templates and a chat API. Start an instance from Hermes, OpenClaw, Claude Code, Codex and others, then talk to it through one chat API.
Where boat fits
Look at boat when your agents do hours of real work that can go wrong: installs, builds, Docker and emulators, with a screen to check their work. boat gives every sandbox a full VM, state saved every minute, forks of running machines and a 60fps desktop, in the EU.
Docker, systemd and /dev/kvm in every sandbox
On Agent 37 the default type cannot run Docker, and the VM type costs 2.5 times as much with no init system. exe.dev has Docker and systemd, but /dev/kvm for emulators is Enterprise only.
State saved every minute, and forks
When an agent wrecks an install, exe.dev has no snapshot to roll back to, and Agent 37 only restores a backup in place and has no fork. boat snapshots every minute and forks a running sandbox to try several paths at once.
A screen your agents can use
exe.dev VMs are headless, so you set up and stream a desktop yourself. Agent 37 needs a template build for a noVNC desktop. boat streams a 60fps desktop with Chromium in every sandbox.
Use boat when your agents do real work for hours: Docker, emulators and a desktop on a full VM, with state saved every minute and forks of running machines. Compare it one to one: boat vs exe.dev and boat vs Agent 37.
Questions people ask
Is exe.dev cheaper than Agent 37?
No. Agent 37's bill is lower in all five scenarios in our table, for example $329 against $1,848 a month for 50 agents in parallel. exe.dev's Personal pools bill whether used or not, while Agent 37 meters per minute.
Which is faster, exe.dev or Agent 37?
We can't say. Neither is in the hpc-sandbox-benchmarks run, so there is no comparable CPU measurement. Agent 37 sells a Performance type on dedicated cores for steady speed.
Can I run Docker on exe.dev and Agent 37?
On exe.dev, yes, in every VM. On Agent 37, only on the VM type, which bills compute at 2.5x the default rate; the default gVisor type cannot run a Docker daemon. On boat, Docker works in every sandbox.
Is an Agent 37 sandbox a VM like exe.dev?
Not by default. Agent 37's default instance is a container enforced by gVisor, and a VM type with its own kernel is opt-in. Every exe.dev machine is a KVM VM, and so is every boat sandbox.
Where do exe.dev and Agent 37 run?
exe.dev has nine regions in the US, Europe, Asia and Australia. Agent 37 runs on dedicated servers in the United States. boat runs only in the EU, in Germany, Finland and France, with EU data residency.
Can either one sleep an idle agent and keep its memory?
Agent 37 can: an instance sleeps after a quiet period, checkpoints its memory and wakes on the next request. exe.dev VMs run until you stop them, and a stopped standalone VM keeps its disk. boat keeps the disk of a stopped sandbox and reboots on resume.
Try boat
Install the CLI, then run boat new.
7-day free trial