smol machines vs Instabox

Both give each agent its own Linux microVM with its own kernel and Docker inside. smol machines is a paid cloud on an open-source engine that can branch a running machine, while Instabox is a free invite-only beta with one machine size, SSH and a desktop.

The companies and products

smol machines

smol machines makes fast, 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, where each machine has its own guest kernel. smol cloud is the paid hosted service that runs fleets of those machines behind a REST API and Node, Python and Rust SDKs. It is built for developers who want one VM model from local development to production, with live branching of running machines.

Isolation: Hardware-isolated microVM with its own guest kernel (libkrun)
Company: Founded 2026, Y Combinator Spring 2026, San Francisco, team of one listed
Open source: smolvm engine and smol SDK are open source and run on macOS, Linux and Windows hosts
Guests: Linux only; no Windows or macOS guests
Regions: No region field in the cloud create API
Uptime SLA: 99.95% on Pro, Startup and Enterprise

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
Machine size: 4 vCPUs and 8 GiB of memory, the same for every machine; 20 GB storage
Machines per account: 5, in any state: paused and stopped ones count
Price: Free during the beta; no published price yet
Access: Invite-only beta; sign in with GitHub or Google
Regions: Not published; more regions are on the roadmap as an idea
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. “12th cheapest of 345” means 11 of the other 344 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	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 a set-up machine often: smol machines branches a running one with its memory, Instabox copies only a stopped one, and boat forks a running sandbox and adds /dev/kvm.	73rd of 367, with limits $604 a month	No published price	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine needs a desktop and keys it cannot leak; Instabox has a desktop, smol cloud has neither, and boat has both built in.	148th of 366, with limits $1,038 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 smol machines fits short code runs well, with a one-minute minimum and a /code endpoint, while Instabox caps an API exec call at 10 minutes with 4 at once.	12th cheapest of 345 $140 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 smol machines holds up to 1,000 machines on Startup, while Instabox allows 5 per account, paused and stopped ones included, so it cannot yet give a sandbox to each of many users.	7th cheapest of 361 $531 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 smol machines can branch a running machine with its memory and processes, so many rollouts start from one prepared state; Instabox forks only stopped machines.	111th of 360, with limits $6,978 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 limits how many evals run at the same time, while smol machines allows 20 to 1,000 by plan.	36th cheapest of 364 $670 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 jobs that build Android apps or boot VMs need nested virtualization, which boat exposes, smol cloud does not, and Instabox does not document.	66th cheapest of 377 $514 a month	No published price	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	216th of 368, with limits $29 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 Instabox has a Linux desktop with screenshot and click control, smol cloud has no hosted desktop, and boat streams one at 60fps with a computer-use agent.	90th of 369, with limits $156 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	176th of 367, with limits $136 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	241st of 346, with limits $242 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	148th of 338, with limits $4,344 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	252nd of 360, with limits $377 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	smol machines	Instabox	boat
Isolation	libkrun microVM with its own guest kernel	Firecracker microVM with its own kernel and root	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine sizes	Up to 8 vCPU / 16 GB on Standard, 16 vCPU / 24 GB on Pro, 32 vCPU / 32 GB on Startup	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
Machines per account	20 on Standard, 100 on Pro, 1,000 on Startup; stopped machines hold a slot	5, in any state: paused and stopped ones count	No session cap on paid plans; starts are limited per minute, hour and day
Docker	Docker runs inside; its data must live on the machine's ext4 disk	Docker and Docker Compose run inside	Docker and Compose run inside, with root and systemd
Nested virtualization	Not exposed in the cloud create API; a local smolvm flag only	Not documented	Yes, /dev/kvm for Android emulators and VMs
Fork	Branch a running machine with its memory and processes; checkpoints capture RAM to a file	Fork copies a stopped machine only	Fork a running sandbox with its disk
Stop, pause and wake	Filesystem survives a stop and disk keeps billing; a command starts a stopped machine, idle apps wake on the next request	Pause keeps memory and running programs and usually resumes in about a second; machines pause after 30 idle minutes by default	Disk is saved every minute and on stop; a stopped sandbox costs nothing
Shell access	Command API, sessions and a WebSocket terminal capped at one hour per connection; no SSH	SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh	SSH, plus a command API and terminal
Inbound access	Up to 16 published ports through a returned URL or an authenticated connect route	HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Outbound rules	Blocked, open, or an allowlist of hosts and CIDR ranges	Not documented	Open internet, no provider-side allowlist
Desktop and computer use	No hosted desktop; a guide shows running your own Chromium inside a machine	Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model	Linux desktop streamed at 60fps, with Chromium and a computer-use agent built in
Coding agents	Registry images with the Codex CLI and the Harbor eval harness, run through the command API	Templates and saved agent sign-ins in snapshots; you run the agent yourself	Seven agents preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandbox	Cloud secrets are environment variables the guest can read; placeholder swapping exists only in self-hosted smolvm	Vault writes your secrets into each machine as environment variables or files	Credentials proxy: real keys never enter the sandbox, for model providers and any HTTPS API
Regions	No region choice in the cloud API	Not published	EU only (Germany, Finland, France), with EU data residency

Every feature Battleships tracks (43)

Feature	smol machines	Instabox	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	No	Not published	Yes
Root	Not published	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	Yes	Yes
Browser	No	Yes	Yes
Computer-use API	No	Yes	Yes
SSH	No	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	Yes	No	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	Yes	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	Not published	Not published	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Not published	No
Secret proxy	No	No	Yes
Secret proxy for any API	No	No	Yes
Preinstalled agents	Yes	Not published	Yes
Agent harness API	No	Not published	Yes
MCP server	Yes	Not published	No
GPU	No	No	No
Windows	No	No	No
Arm64	Yes	Not published	No
Self-hosting	Yes	Not published	No
BYOC	Yes	Not published	No
Open source	Yes	No	No
Scoped API keys	Not published	Yes	Yes
Spend limits	Yes	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	No	Not published	Yes
Zero data retention	Not published	Not published	Yes

Performance

smol machinesNot measured

InstaboxNot measured

boat26.69 runs/s

There is no comparable measurement for smol machines or Instabox: neither has been run on the hpc-sandbox-benchmarks CPU test, so 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. smol machines publishes a boot time under 200ms for smolvm, and Instabox says its shell is ready in under a second; both are start times, not CPU speed, and neither was measured here.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. smol machines 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	smol machines, 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	$25 · Standard	No published price	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$93 · Standard	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	$1,139 · Pro	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	$465 · Startup	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	$1,389 · Startup	No published price	$2,000 · $2000/mo · with limits

smol machines: smol cloud charges a base fee for every hour a machine runs, plus the CPU and memory the guest actually uses, with a one-minute minimum and disk billed even while stopped. Pro ($20 a month) and Startup ($150 a month) are fees on top of usage, not credit.

Instabox: Instabox is free during the beta, with 5 machines per user, and publishes no price yet, so no bill can be compared with smol machines or boat.

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

smol machines caps how many machines you hold by plan: 20 on Standard, 100 on Pro and 1,000 on Startup, with stopped machines still holding a slot, so 50 agents need Pro and 1,000 short jobs at once need Startup. Instabox allows 5 machines per account in any state, all 4 vCPU / 8 GiB, so the 50-agent, user-sandbox and burst scenarios do not fit it today, and it has no price for any scenario. boat's limit that bites is starts: for 1,000 short jobs at once, the $2,000 plan queues starts above 90 a minute.

Scenario	smol machines	Instabox	boat
One coding agent, workdays	None that bite	no published per-resource rate	None that bite
One agent that never stops	None that bite	no published per-resource rate	None that bite
50 agents in parallel	None that bite	no published per-resource rate	None that bite
Sandboxes for your users	None that bite	no published per-resource rate	None that bite
1,000 short jobs at once	None that bite	no published per-resource rate	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use smol machines when

you want one open-source VM engine from your laptop to your own servers, branch running machines with their memory, or need more than five machines.

Open source, from laptop to your own servers. Teams that want the same VM locally, in a hosted cloud and on their own servers get it from one open-source engine.
Live branches with memory. Useful for RL and test fan-out: branch a running machine with its memory and processes, paying the one-minute minimum once.
Room for a fleet. Teams running many agents can hold up to 1,000 machines on Startup, up to 32 vCPU each, with outbound allowlists.

Use Instabox when

you want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with SSH, mosh, a desktop and pause with memory.

Free during the beta. For trying things out, 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, per its docs, usually resumes in about a second.
SSH, mosh and a desktop. Developers who live in a terminal get SSH through a gateway with mosh, and a Linux desktop on one template.

Where boat fits

If your agents need a whole machine and not just a VM boundary, look at boat. It adds /dev/kvm, keys that never enter the sandbox, private port URLs and coding agents you drive from outside, which neither smol machines nor Instabox gives you today.

Emulators and VMs inside the sandbox

An agent that builds Android apps or boots a VM needs /dev/kvm. smol cloud does not expose it and Instabox does not document it; on smol you would have to run smolvm on your own servers.

Keys a prompt injection cannot read

Both put your secrets inside the machine: smol cloud as environment variables, Instabox as variables or files. One injected prompt can leak them. smol's placeholder swapping only works if you self-host smolvm.

Agents you drive from outside

On both you install the agent and write your own harness on exec calls or SSH. boat ships seven coding agents and lets you prompt, steer and follow them through one API, with token-protected URLs for what they serve.

Use boat when your agents need a whole machine: Docker, emulators, SSH, a 60fps desktop, private port URLs, coding agents you drive from outside and keys that never enter the sandbox. Compare it one to one: boat vs smol machines and boat vs Instabox.

Questions people ask

Is smol machines cheaper than Instabox?

It can't be compared yet. Instabox is free during its beta, with 5 machines per user, and publishes no price, so there is no bill to set against smol machines' usage pricing. smol machines' prices for each scenario are in the table above.

Which is faster, smol machines or Instabox?

Neither has a CPU measurement, so this page makes no speed claim between them. smol machines publishes a boot time under 200ms for smolvm, and Instabox says its shell is ready in under a second; neither was measured here.

Can smol machines and Instabox run Docker?

Yes, both run Docker inside the VM; smol's guide says Docker data must live on the machine's ext4 disk. For Android emulators or nested VMs, smol cloud does not expose nested virtualization and Instabox does not document it, while boat exposes /dev/kvm.

Can either fork a running machine?

smol machines can: it branches a running machine with its memory and processes. 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 with its disk.

Do smol machines and Instabox have SSH?

Instabox does, through a gateway with short-lived certificates, plus mosh and paste-anywhere SSH tokens. smol cloud has no SSH; you use its command API or a WebSocket terminal capped at one hour per connection.

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.

Try boat

Install the CLI, then run boat new.

7-day free trial