smol machines vs Agent 37
smol machines gives every machine its own microVM kernel, from an open-source engine you can also run on your own servers, and it can branch a running machine with its memory. Agent 37 hosts one always-on agent per user in lighter gVisor sandboxes that sleep when idle, keep their memory and cost less per hour, with a full VM type as an option.
The companies and products
smol machines
smol machines makes isolated Linux microVMs that run the same way on your laptop, in their hosted cloud, or on your own servers.
The core is smolvm, an open-source microVM engine built on libkrun. Each machine has its own guest kernel. smol cloud is the paid hosted service. It runs machines behind a REST API, Node, Python and Rust SDKs, and a managed agents API. It is for developers who want one VM model from local development to production, with live branching of running machines.
- Uptime SLA
- 99.95% on Pro, Startup and Enterprise
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.
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. “41st cheapest of 361” means 40 of the other 360 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 | smol machines: 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 smol machines runs Docker in every machine. Agent 37 runs Docker on its VM type, which bills compute at 2.5 times the default rate. In our default preset Agent 37 ranks 5th, boat 8th, and smol machines is listed as a compromise because you add the desktop yourself. | 105th of 365, with limits $604 a month | 4th cheapest of 365 $551 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 is built for this: one assistant per user that sleeps when idle, keeps its memory and wakes on the next message. In our default preset it ranks 1st at $279 a month, boat 5th at $657 and smol machines 8th at $1,038. | 41st cheapest of 361 $1,038 a month | Cheapest of 361 $279 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Both fit short code runs. Agent 37 ranks 1st in our default preset with small low-cost default sandboxes, and smol machines ranks 12th with a one-minute minimum and a /code endpoint for Python and JavaScript. boat's start limits make big bursts a compromise. | 16th cheapest of 336 $140 a month | Cheapest of 336 $22 a month | 189th of 336, 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 smol machines holds up to 1,000 machines on Startup, and Agent 37 runs up to 1,000 awake instances once you have topped up $1,000. In our default preset Agent 37 ranks 1st, boat 2nd and smol machines 10th. | 12th cheapest of 349 $531 a month | Cheapest of 349 $79 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month smol machines can branch a running machine with its memory and processes, so many rollouts start from one prepared state. Agent 37 forks an instance's disk, and the fork boots fresh. In our default preset Agent 37 ranks 9th, boat 29th and smol machines 80th. | 119th of 349, with limits $6,978 a month | 9th of 349, with limits $363 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 49th cheapest of 359 $670 a month | Cheapest of 359 $58 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 69th cheapest of 374 $514 a month | 227th of 374, with limits $96 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Agent 37 is low-cost to keep around the clock and takes SSH through a WebSocket tunnel; it ranks 3rd at $12 a month. smol cloud documents no SSH route. boat ranks 13th at $26 with a full VM, systemd and SSH. | 230th of 371, with limits $29 a month | 3rd cheapest of 371 $12 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Agent 37 offers a noVNC desktop through a template and ranks 1st in our default preset. On smol cloud you install a desktop and a screen stream in your own image. boat ships a 60 fps desktop with computer-use tools and ranks 8th. | 135th of 367, with limits $156 a month | 3rd cheapest of 367 $120 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 58th of 356, with limits $136 a month | 47th of 356, with limits $29 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 97th cheapest of 343 $242 a month | Cheapest of 343 $32 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 145th of 327, with limits $4,344 a month | 39th of 327, with limits $648 a month | 73rd of 327, 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 ranks 1st in our default preset on its VM type and can fork an instance's disk. smol machines can branch a running machine with its memory. boat ranks 5th and forks a running sandbox from its last 1-minute snapshot. | 59th of 351, with limits $377 a month | Cheapest of 351 $43 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | smol machines | Agent 37 | boat |
|---|---|---|---|
| Isolation | libkrun microVM with its own guest kernel | gVisor by default; full VM as an opt-in instance type | Full VM with its own kernel on AMD Ryzen hosts dedicated to boat; vCPUs are shared |
| Docker inside | Yes, with Docker data on the machine's ext4 disk | Yes on the VM type, at 2.5x the default compute rate; the default gVisor type cannot run a Docker daemon | Yes, in every sandbox |
| Nested virtualization | Yes on Startup ($150 a month plus usage) and Enterprise; refused on Standard and Pro | /dev/kvm on the VM type, with a ready Android template | /dev/kvm in every sandbox on every plan; the Android emulator works |
| Shell access | Command API, sessions and a WebSocket terminal capped at one hour per connection; no SSH route documented | Exec API and SSH through an authenticated WebSocket tunnel | SSH, plus a command API and terminal |
| Idle and wake | A command or terminal starts a stopped machine; idle apps wake on the next request | Opt-in auto-sleep after a quiet period (default 15 minutes), wakes on the next request | No idle timer; auto-stop runs on a timer from creation or resume (default 1 hour, up to 30 days, or off on a paid plan) |
| Memory kept | Checkpoints capture a running machine with its RAM to durable storage | Memory checkpointed on auto-sleep; processes resume when the restore works, otherwise it boots fresh with its disk | Disk saved every minute and at stop; memory is not saved, so a resume is like a reboot |
| Fork | Branch a running machine with its memory and processes | Fork any running, stopped or sleeping instance (disk copy, the fork boots fresh); nightly backups in 7 slots plus one on-demand | Fork a running sandbox from its last 1-minute snapshot (the fork boots fresh); saved snapshots that new sandboxes start from |
| Stopped machines | Filesystem in /workspace and the image survives a stop; disk bills at $0.0001/GB-hour while stopped | Disk kept; disk bills at $0.09 per GB a month while stopped or asleep | No compute charge while stopped; disk kept at least 14 days, longer as a saved snapshot. Extra saved snapshots and the AI credentials proxy still bill |
| Desktop and browser | You set it up: run Chromium from an OCI image (official guide), and add a desktop and screen stream yourself | You set it up: noVNC desktop through a template build, or the Ubuntu VM template | Built-in Linux desktop and Chrome streamed at 1920x1080, 60 fps, with computer-use tools |
| Built-in agents | Managed agents API: Claude Code, Codex, OpenCode or any command as the harness, with turns, event stream, rewind and branch | Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API per instance | Seven harnesses installed, with a prompt, steer and events API |
| Keeping API keys out | Stored credentials: the guest sees a placeholder, and the real value is swapped in on HTTPS to allowed hosts; plain env secrets are readable | Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars | Optional AI credentials proxy ($1 a day it is on, plus $1 per 1,000 requests) for supported providers and HTTPS APIs you register; other secrets still enter |
| Inbound access | Up to 16 published ports via token URLs or an authenticated route, plus a TCP tunnel route; no dedicated IP | HTTPS URL per port, signed URLs, public ports, custom domains; no public IP | Up to 50 token-gated HTTPS URLs per sandbox, public IPv6, SSH over IPv4; the IP changes at each resume |
| Outbound rules | Blocked, open, or an allowlist of hosts and CIDR ranges | Open internet | Open internet, no provider-side allowlist |
| Where it runs | No region choice in the cloud API; open-source smolvm runs on your own servers | Dedicated servers in the United States | Germany, Finland and France; you cannot pick a region, and snapshot copies can be stored outside the EU |
Every feature Battleships tracks (43)
| Feature | smol machines | Agent 37 | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No documented way | Yes |
| Docker inside | Yes | No documented way | Yes |
| Nested virtualization | Yes | No documented way | Yes |
| Root | Not published | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No documented way | With your own setup | Yes |
| Browser | With your own setup | Yes | Yes |
| Computer-use API | No documented way | No documented way | Yes |
| SSH | No documented way | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No documented way | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | Yes | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Not published | Not published | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | No documented way | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | Yes | No documented way | No documented way |
| GPU | No documented way | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | Yes | No documented way | No documented way |
| Self-hosting | Yes | No documented way | No documented way |
| BYOC | Yes | No documented way | No documented way |
| Open source | Yes | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No documented way |
| SSO | Yes | No documented way | No documented way |
| SOC 2 | No documented way | Yes | No documented way |
| HIPAA | No documented way | No documented way | No documented way |
| EU data residency | No documented way | No documented way | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
smol machines and Agent 37 are not in the public benchmarks we use, so we cannot say which of the three is faster. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in that run ran on an AMD Ryzen 9 9950X host; boat also places sandboxes on Ryzen 7 9700X hosts and does not promise a CPU model. smol machines publishes a boot time under 200 ms for smolvm, which is a start time, not CPU speed. Agent 37 says its default instances share host resources and sells dedicated cores at 4x the rate.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. smol machines and Agent 37 are not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | smol machines, 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 | $25 · Standard | $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 | $93 · Standard | $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 | $1,139 · Pro | $329 · Wallet ($50 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 | $465 · Startup | $33 · Wallet ($1,000 lifetime top-ups) | $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 | $1,389 · Startup | $73 · Wallet ($1,000 lifetime top-ups) · with limits | $8,800 · $2000/mo · with limits |
smol machines: smol cloud charges $0.04 for every hour a machine runs, plus $0.05 per active vCPU-hour and $0.0162 per active GB-hour of memory, with a one-minute minimum. Disk bills at $0.0001 per GB-hour, also while stopped. Pro ($20 a month) and Startup ($150 a month) are fees on top of usage, not credit.
Agent 37: A prepaid wallet with no plan fee, metered per minute on allocated size: $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 stopped or asleep. VM compute costs 2.5x and Performance compute 4x.
Agent 37: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month; unused included time expires. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second at full rate, busy or idle. A stopped sandbox has no compute charge, but saved snapshots above the included count and the AI credentials proxy still bill. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07.
Limits in those scenarios
smol machines caps machines held and running by plan: 20 on Standard, 100 on Pro and 1,000 on Startup, and a stopped machine still holds a slot, so 1,000 short jobs at once needs Startup. Agent 37 caps awake instances at 3 before your first top-up, then 10, 50, 200 and 1,000 as total top-ups reach $1,000; sleeping and stopped instances do not count. Agent 37 does not publish an egress price. On boat, the 1,000-job burst needs about 6,667 starts a day, above the 2,400 that the $2,000 plan includes, so extra starts are paid. Starts above 270 a minute fail with 429, and boat never queues a start.
| Scenario | smol machines | Agent 37 | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario |
| None for this scenario |
| One agent that never stops | None for this scenario |
| None for this scenario |
| 50 agents in parallel | None for this scenario |
| None for this scenario |
| Sandboxes for your users | None for this scenario |
| None for this scenario |
| 1,000 short jobs at once | None for this scenario |
|
|
Which one should you use?
Use smol machines when
you want one open-source VM engine from your laptop to your own servers, need outbound allowlists or secrets kept out as placeholders, or fan out branches of a running machine with its memory.
- Open source, from laptop to your own servers. Teams that want one VM engine locally, in a hosted cloud and on their own servers can use open-source smolvm.
- Live branches with memory. Useful for RL and test fan-out: branch a running machine with its memory and processes into many children.
- Outbound allowlists and secrets kept out. Teams that must limit which hosts a machine reaches, or keep any secret out of the guest as a placeholder, get both on smol cloud.
Use Agent 37 when
you host one mostly idle assistant per customer in the US that should sleep with its memory kept and wake on the next message, at a low hourly rate.
- 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.
- Low cost for one agent per user. Teams hosting many small, mostly idle agents pay the lowest bill here in most scenarios, with no plan fee.
- Bring a Dockerfile, pick dedicated cores. Agent 37 builds templates from your own Docker image, and sells a Performance type on dedicated cores.
Where boat fits
For agents that do real work for hours, like installs, builds, tests, Docker and emulators, look at boat. Every sandbox is a full VM with systemd, SSH, /dev/kvm and a 60 fps desktop on every plan, billed per second.
Docker, emulators and SSH in every sandbox
smol cloud exposes nested virtualization only on Startup and Enterprise, and documents no SSH route. Agent 37 has /dev/kvm and Docker on its VM type, which bills 2.5 times the compute and has no init system. boat has all of these on every sandbox.
A desktop ready for computer use
On smol cloud you build and run your own desktop and screen stream before an agent can click anything. Agent 37 adds a noVNC desktop through a template build. boat streams a 60 fps desktop with Chrome.
Lower monthly price for steady work
For one agent running all month, boat costs $26 against $93 on smol machines; Agent 37 costs $12. boat bills $0.036 an hour for 4 vCPU / 8 GB, busy or idle, from a $20 plan. A stopped sandbox has no compute charge and keeps its disk for at least 14 days.
Use boat when your agents need a whole machine on every plan: Docker, /dev/kvm for emulators, SSH, a built-in desktop and browser, and coding agents you drive from outside, at a flat per-second price for steady work. Compare it one to one: boat vs smol machines and boat vs Agent 37.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is smol machines cheaper than Agent 37?
No, not in the scenarios on this page. Agent 37 comes out lower in all five, for example $12 against $93 a month for one agent running 24/7. For the 1,000-job burst, Agent 37's default type runs on shared vCPUs, which our table marks as a compromise. boat comes to $26 for the 24/7 agent; its smallest commitment is $20 a month.
Which is faster, smol machines or Agent 37?
Neither is in the public benchmarks we use, so we cannot say. smol machines publishes a boot time under 200 ms for smolvm, which is about start time, not CPU speed. boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB in StarSling's run of 3 October 2026, on a Ryzen 9 9950X host.
Can smol machines and Agent 37 run Docker?
smol machines runs Docker inside every machine, with Docker data on the ext4 disk. Agent 37 runs Docker on its VM type, which bills compute at 2.5x; the default gVisor type cannot run a Docker daemon. boat runs Docker in every sandbox.
Is Agent 37 a VM like smol machines?
By default no: an Agent 37 instance is a container enforced by gVisor, and a full VM is an opt-in type. Every smol machine is a libkrun microVM with its own kernel, and every boat sandbox is a full VM.
Can either fork a running machine?
Yes, both. smol machines branches a running machine into children that keep its memory and processes. Agent 37 copies the disk of a running, stopped or sleeping instance, and the fork boots fresh. boat forks a running sandbox from its last 1-minute snapshot; writes from the last minute or so can be missing.
Where do smol machines and Agent 37 run?
Agent 37 runs on dedicated servers in the United States. smol cloud has no region choice in its API, but smolvm can run on your own servers. boat runs on machines in Germany, Finland and France; you cannot pick a region, and snapshot copies can be stored outside the EU.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs smol machines
- boat vs Agent 37
- E2B vs smol machines
- Daytona vs smol machines
- Modal vs smol machines
- Vercel Sandbox vs smol machines
- Cloudflare Sandbox vs smol machines
- Blaxel vs smol machines
- Runloop vs smol machines
- Tensorlake vs smol machines
- Morph Cloud vs smol machines
- CodeSandbox SDK vs smol machines