Sprites vs Instabox
Sprites and Instabox both give each agent its own Firecracker microVM with root and Docker. Sprites is a metered product that sleeps when idle and wakes on the next request, while Instabox launched today as a free, invite-only beta with one machine size, five machines per account and a desktop for computer use.
The companies and products
Sprites
Sprites is Fly.io's product for agents: persistent Linux computers you create by API or CLI, which sleep when idle and wake on the next request.
Each Sprite is a Firecracker microVM with 8 vCPU, memory the platform manages, and a 100 GB ext4 disk that syncs to object storage. It runs one managed Ubuntu image with Claude Code, Codex, Gemini CLI and Cursor preinstalled, gets an HTTPS URL that wakes it, and bills only for the CPU and memory it actually uses while awake. It is built for coding agents, dev environments and user code that sit idle most of the time.
- Isolation
- Firecracker microVM per Sprite
- Regions
- Not selectable for Sprites
- Free start
- $30 trial credit per organization
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. “63rd cheapest of 377” means 62 of the other 376 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 | Sprites: 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 Sprites gives every machine 8 vCPU and a 100 GB disk, while Instabox has one 4 vCPU / 8 GiB size with 20 GB; boat forks a running sandbox and goes up to 16 vCPU / 32 GB. | 66th of 367, with limits $546 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB A Sprite stays billed only while something holds it awake and drops open connections on every pause; Instabox pauses after 30 idle minutes unless you turn that off, and boat just keeps running. | 157th of 366, with limits $1,166 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 Sprites suits short code runs: it sleeps about 30 seconds after the last command and bills only real CPU and memory; an Instabox API exec call runs at most 10 minutes, 4 at once. | 93rd of 345, with limits $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 Instabox allows 5 machines per account, paused and stopped ones included, so it cannot give a sandbox to each of many users; Sprites does not publish a pay-as-you-go running cap. | 56th of 361, with limits $428 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 | 105th of 360, with limits $6,540 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 once; Sprites lists running caps on its plans, and boat has no session cap on paid plans. | 125th of 364, with limits $545 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, which boat exposes and neither the Sprites nor the Instabox docs mention. | 63rd cheapest of 377 $476 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Instabox has an SSH gateway with mosh, while Sprites tunnels SSH through its CLI; boat has SSH, systemd and a published price. | 213th of 368, with limits $27 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 Computer-use agents need a screen: Instabox has a desktop on one template, Sprites is headless, and boat streams a 60fps desktop with Chromium. | 85th of 369, with limits $136 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 | 171st of 367, with limits $122 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 | 229th of 346, with limits $206 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 | 141st of 338, with limits $4,113 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 | 210th of 360, with limits $223 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 | Sprites | Instabox | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | Fixed 8 vCPU and 100 GB disk; memory set and scaled by the platform | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage | You choose; up to 16 vCPU / 32 GB on the $100 plan and above |
| How many machines | Pay-as-you-go running cap not published; plans list running caps | 5 per account, paused and stopped ones included | No session cap on paid plans; start limits per plan |
| Docker and systemd | Root and Docker (with rough edges users report); no systemd | Root, Docker and Docker Compose; systemd not documented | Root, Docker, Compose and systemd |
| Nested virtualization | Not in the docs | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Idle and wake | Pauses about 30 seconds after activity stops and wakes on the next request, in 100 to 500 ms with memory | Pauses after 30 idle minutes by default, keeping memory; resume usually takes about a second; a visit does not wake it | Runs until you stop it; a stopped sandbox costs nothing and keeps its disk |
| Snapshots | Filesystem checkpoints by hand or automatic; restore replaces the disk in place | Saved by hand, up to 10; saving stops a running machine first unless the server allows a live save | Disk saved every minute and on stop, plus named snapshots |
| Fork | No fork in the public API or CLI | Fork copies a stopped machine | Fork a running sandbox with its disk |
| Public URLs | One HTTPS URL to one HTTP port, private by default | HTTPS on up to 16 ports, open to anyone with the URL; offline while paused | HTTPS on up to 50 ports, token-protected by default; raw TCP too |
| SSH | Only through the sprite proxy CLI, with an SSH server you install | SSH gateway with short-lived certificates, paste-anywhere tokens and mosh | SSH into every sandbox, with a dedicated IP |
| Desktop and computer use | Headless; no desktop or browser product | Linux desktop with a browser on one template, screenshot and click API; you bring the model | 60fps Linux desktop with Chromium and a computer-use agent |
| Keeping API keys out of the sandbox | Connectors gateway holds the token for any HTTP API, with path allow and block lists | Vault writes your secrets into each machine as environment variables or files | Credentials proxy for model providers and any HTTPS API; real keys never enter the sandbox |
| Outbound rules | Optional DNS-based domain allowlist; private IPs always blocked | Not documented | Open internet, no provider-side allowlist |
| Coding agents | Claude Code, Codex, Gemini CLI and Cursor preinstalled, run through exec | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Seven agents preinstalled, with a prompt, steer and events API to drive agents inside from outside |
Every feature Battleships tracks (43)
| Feature | Sprites | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | 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 | Yes | No | Yes |
| Fork/clone | No | Yes | Yes |
| Live fork (no pause) | No | No | Yes |
| Memory fork | No | 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 | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | 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 | No | 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 | No | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | Yes | Not published | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Sprites nor Instabox has a comparable measurement: neither is in the hpc-sandbox-benchmarks results we use, so this page makes no speed claim between them. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Instabox says a new machine's shell is ready in under a second, and Sprites says a sleeping Sprite wakes in 100 to 500 ms; 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. Sprites 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 | Sprites, 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 | $23 · Pay-as-you-go | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $92 · Pay-as-you-go | 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 | $1,120 · Pay-as-you-go | 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 | $314 · Pay-as-you-go · 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 | $1,134 · Pay-as-you-go · with limits | No published price | $2,000 · $2000/mo · with limits |
Sprites: Sprites bills CPU time at $0.0385 per CPU-hour and actual memory at $0.021875 per GB-hour, only while the Sprite is awake, plus storage on the bytes you write. Optional plans include fixed CPU, memory and storage allowances that are not credit.
Instabox: Instabox is free during the beta ("Free until we figure it out"), with 5 machines per user, and has no published price yet, so no bill can be compared with Sprites 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
Instabox allows 5 machines per account, paused and stopped ones included, so the 50-agent, user-sandbox and burst scenarios do not fit it today, and an API exec call runs at most 10 minutes, 4 at once. Sprites does not publish how many Sprites can run at once on pay as you go, so 300 user sandboxes and 1,000 jobs at once are not confirmed, and an always-on agent needs a task hold renewed at least every hour. boat has no session cap on paid plans, but at 1,000 short jobs at once even its $2,000 plan queues starts and runs out of daily starts.
| Scenario | Sprites | Instabox | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Sprites when
your agents or apps sit idle most of the day and should wake on a request, or when you need a domain allowlist on outbound traffic and a bill you can plan.
- Wakes on request. For agents and apps idle most of the day: a Sprite sleeps after about 30 seconds and wakes on the next request.
- A bigger machine and a published bill. Every Sprite has 8 vCPU and a 100 GB disk, and it bills only the CPU and memory it actually uses.
- Egress allowlist and API connectors. Sprites can limit which domains an agent reaches and which API paths it may call through a stored token.
Use Instabox when
you want to try up to five free 4 vCPU / 8 GiB agent machines during its beta, with a desktop, memory pause and mosh.
- Free during the beta. During the invite-only beta, each account can run 5 machines of 4 vCPU / 8 GiB for free.
- A desktop for computer use. One template has a Linux desktop with a browser, a screenshot and click API, and shareable view or control links.
- SSH gateway with mosh. Its SSH gateway relays mosh and gives paste-anywhere SSH tokens, so a terminal session survives sleep and network changes.
Where boat fits
Sprites is built for machines that sleep most of the day, and Instabox is a new free beta with five machines of one size. If your agents work for hours, need to branch their work, or run as a fleet, boat gives each one a full VM you can size, fork while it runs and drive from outside, on terms that are published today.
A full machine, not a fixed box
Neither Sprites nor Instabox documents /dev/kvm, and Sprites has no systemd, so Android emulators, nested VMs and systemd services do not work as on a normal server. boat runs all three, at sizes you pick up to 16 vCPU / 32 GB.
Fork running work
Sprites has no fork, and Instabox forks only a stopped machine, which ends the agent's running programs. On boat you fork a running sandbox, so the original keeps working while the copy tries another approach.
Fleets and private URLs
Instabox caps an account at 5 machines and its port URLs are open to anyone; Sprites gives one HTTP port and does not publish its pay-as-you-go running cap. boat has no session cap on paid plans and token-protected URLs on up to 50 ports.
Use boat when your agents need a full machine for hours: systemd, Docker, /dev/kvm, a size you choose, forks of running work, private URLs on many ports, a 60fps desktop, and an API to drive agents inside from outside. Compare it one to one: boat vs Sprites and boat vs Instabox.
Questions people ask
Is Sprites cheaper than Instabox?
It can't be compared yet. Instabox is free during the beta and has no published price, so there is no bill to set against Sprites. Sprites bills real CPU and memory use while awake; one coding agent on workdays comes to $23 a month on Sprites and $20 on boat.
Which is faster, Sprites or Instabox?
Neither has been benchmarked in the results we use, so we make no speed claim. Sprites says a sleeping Sprite wakes in 100 to 500 ms, and Instabox says a new machine's shell is ready in under a second. boat measured 26.69 runs per second at 4 vCPU / 8 GB.
Can Sprites and Instabox run Docker?
Both run Docker inside the VM with root. Sprites does not run systemd and users report rough edges with some containers; Instabox documents Docker Compose. boat runs Docker, Compose, systemd and /dev/kvm.
Can I fork a machine on Sprites or Instabox?
Sprites has no fork in its public API or CLI, and its checkpoints restore in place. Instabox's fork copies a stopped machine only. boat forks a running sandbox with its disk.
Do Sprites or Instabox have a desktop for computer use?
Instabox has a Linux desktop with a browser on one template, with a screenshot and click API, and you bring the model. Sprites is headless. boat streams a 60fps desktop with Chromium and a computer-use agent.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Try boat
Install the CLI, then run boat new.
7-day free trial