boat vs Replit

Replit is a place where people describe an app, Replit Agent builds it, and Replit hosts it. boat is for the other side: your own code creates full Linux VMs by API, with Docker, a desktop and coding agents you drive from outside.

Where boat stands out

Machines your code creates

On boat your program creates a full Linux VM by API, runs work in it, forks it while it runs, and stops it. Replit starts from a person and a chat: from the outside you can ask Replit Agent to create or change an app through its MCP server, but there is no API to start many machines.

Root, Docker and KVM

Every boat sandbox has root, systemd, Docker and /dev/kvm on its own kernel. Replit sets up environments with Nix packages, and its docs do not describe running Docker, systemd services or virtual machines inside.

Your agents, driven from outside

boat ships Claude Code, Codex, OpenCode and other agents in each sandbox, with a prompt, steer and events API so your app can start one, correct it mid-task and stream what it does. Its credentials proxy keeps real keys outside the sandbox for any HTTPS API, and a 60fps desktop with Chromium lets agents use a real browser.

The companies and products

boat

boat.dev runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.

You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.

Isolation: Full VM per sandbox, own kernel
Hardware: Dedicated AMD Ryzen 9 9950X (Zen 5) hosts
Regions: EU: Germany, Finland, France
Plans: From $20 a month, all of it usage credit, 7-day trial

Replit

Replit is an AI app builder and hosting platform: you describe an app in chat, Replit Agent writes it, and Replit publishes it.

You work in a browser workspace where Replit Agent sets up the project, writes the code, tests it and fixes problems, with system packages managed by Nix. When the app is ready you publish it as an Autoscale, Static, Scheduled or Reserved VM deployment, with Postgres and object storage next to it. It is built for people and teams who want a working app, not for programs that need to create many machines by API, so this page compares the parts where the two overlap.

Kind of product: AI app builder with workspaces and app hosting, not a sandbox API
Hosting: Data is hosted mainly in Google Cloud data centers in the United States, with an optional India region
Regions for published apps: North America, Europe, Asia, South America and Australia on Core, Pro and Enterprise; the free plan publishes to North America
Isolation: Not documented: the security page promises strong logical separation between users but does not say containers or VMs
Plans: Starter (free), Core $20 a month, Pro from $100 a month, Enterprise custom; plan fees come back as usage credits
Compliance: Says it has a SOC 2 Type 2 attestation

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. “3rd cheapest of 367” means 2 of the other 366 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	boat: price rank	Replit: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory starts and steers many agents from code; Replit's outside entry point is an MCP server that drives Replit Agent one app at a time.	3rd cheapest of 367 $634 a month	181st of 367, with limits $2,000 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant on Replit means a Reserved VM, which is one published app that runs and bills all month.	5th cheapest of 366 $657 a month	202nd of 366, with limits $2,033 a month
Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Replit's Autoscale bills only while requests are served and scales to zero, so short code runs cost less there, though it is a web host, not a code runner.	186th of 345, with limits $2,000 a month	228th of 345, with limits $146 a month
Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Replit does not publish how many deployments can run at once, and each one is a published app, so 300 machines for your users is not something it is built for.	Cheapest of 361 $209 a month	233rd of 361, with limits $825 a month
RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month	34th of 360, with limits $2,000 a month	258th of 360, with limits $4,226 a month
Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month	10th cheapest of 364 $200 a month	265th of 364, with limits $685 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build containers need Docker, which boat has on every machine and Replit's Nix-based environments do not document.	4th cheapest of 377 $86 a month	275th of 377, with limits $425 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A Replit workspace is a good place to code by hand, but its CPU and memory per plan are no longer published, and there is no Docker or systemd.	18th cheapest of 368 $26 a month	165th of 368, with limits $109 a month
Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Replit's VNC pane shows a desktop to a person in the workspace, with no API for an agent to take screenshots and click.	6th cheapest of 369 $200 a month	190th of 369, with limits $619 a month
Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month	7th cheapest of 367 $200 a month	229th of 367, with limits $317 a month
Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month	6th cheapest of 346 $90 a month	234th of 346, with limits $217 a month
Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month	71st of 338, with limits $1,800 a month	150th of 338, with limits $4,378 a month
Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month	2nd cheapest of 360 $200 a month	208th of 360, with limits $215 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
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

Key features

Feature	boat	Replit
Kind of product	Sandboxes you create, stop and fork by API, SDK or CLI	AI app builder with browser workspaces and app hosting
Isolation	Every sandbox is a full VM with its own kernel	Not documented; the security page says strong logical separation between users
Creating machines from code	API, SDK and CLI to create, stop, resume and fork many sandboxes	MCP server tools to create, update and publish apps; no API to start many machines
Docker and nested virtualization	Docker, root, systemd and /dev/kvm on every machine	System packages come from Nix; the docs do not describe Docker, systemd or /dev/kvm
Files over time	Disk kept with snapshots every minute and on stop; a stopped sandbox costs nothing	Workspace files and Agent checkpoints at milestones; published apps should not rely on their filesystem
Coding agents	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API	Replit Agent, which you can also drive from an MCP client (create, update, ask, publish)
Keeping keys out of the sandbox	AI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out	Replit manages keys for OpenAI, Anthropic, Google and OpenRouter models, billed to credits; other keys are secrets in the app
Desktop and computer use	60fps desktop and Chromium, computer use and browser control, embeddable stream	VNC pane that streams a native desktop to your browser; no computer-use API
Reaching the machine	HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4; SSH	Published apps on HTTPS domains, custom domains and private deployments; SSH into the workspace on paid plans
Always-on machine	Any sandbox can run for weeks, and stopping it ends the bill	Reserved VM runs continuously at a fixed monthly price per size
Hosting that sleeps when idle	No wake on request; you stop and resume sandboxes yourself	Autoscale starts on the first request and goes idle after 15 minutes, costing nothing while idle
Databases and storage	No hosted databases; run your own inside a sandbox	Postgres and App Storage built into each app
Regions	EU only: Germany, Finland, France	North America, Europe, Asia, South America and Australia for published apps on Core and up
Compliance and transparency	SOC 2 is in progress. We're open about where we stand: live status and data retention policy.	SOC 2

Every feature Battleships tracks (43)

Feature	boat	Replit
Full VM (own kernel)	Yes	Yes
Docker inside	Yes	No
Nested virtualization	Yes	No
Root	Yes	Not published
Systemd	Yes	No
Desktop GUI	Yes	Yes
Browser	Yes	No
Computer-use API	Yes	No
SSH	Yes	Yes
Persistent disk	Yes	Yes
Pause/resume	Yes	No
Automatic snapshots	Yes	Yes
Fork/clone	Yes	Yes
Live fork (no pause)	Yes	No
Memory fork	No	No
Custom image (Docker or snapshot)	Yes	Yes
≥24 h sessions	Yes	Yes
Idle auto-stop	No	Yes
Wake on request	No	Yes
HTTPS preview URLs	Yes	Yes
Raw TCP inbound	Yes	Not published
Public IPv4	No	No
Egress allowlist	No	No
Secret proxy	Yes	Yes
Secret proxy for any API	Yes	No
Preinstalled agents	Yes	Yes
Agent harness API	Yes	Yes
MCP server	No	Yes
GPU	No	No
Windows	No	No
Arm64	No	Not published
Self-hosting	No	No
BYOC	No	No
Open source	No	No
Scoped API keys	Yes	Not published
Spend limits	Yes	Yes
Usage per sandbox (API)	Yes	Yes
Audit logs	No	Yes
SSO	No	Yes
SOC 2	No	Yes
HIPAA	No	No
EU data residency	Yes	Yes
Zero data retention	Yes	Not published

Performance

boat26.69 runs/s

ReplitNot measured

There is no comparable measurement. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's public benchmark, but Replit is not in that benchmark, so we cannot say which is faster.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Replit 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	boat, a month	Replit, 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	$20 · $20/mo	$122 · Pro $100 (annual) · with limits
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$26 · $20/mo	$122 · Pro $100 (annual) · with limits
50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside	$317 · $20/mo × 3 seats	$1,330 · Pro $1,000 (annual) · with limits
Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once	$200 · $100/mo × 2 seats	$403 · Pro $250 (annual) · with limits
1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month	$2,000 · $2000/mo · with limits	$825 · Pro $1,000 (annual) · with limits

boat: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Replit: Replit plans (Core $20, Pro from $100) turn into monthly credits that pay for Agent work and hosting, then usage goes on to pay-as-you-go. A Reserved VM has a fixed monthly price per size, such as $130 for 4 vCPU / 16 GB, and bills whether busy or idle; Autoscale charges $0.60 per million compute units and $0.40 per million requests only while it serves. Our bills price agents as Reserved VMs, the only kind that stays on, and leave out Agent usage.

Limits in those scenarios

Replit is marked as not a fit in every scenario because it is an app platform: one Reserved VM is one published app that runs all month, so 50 agents means 50 published apps, and an agent that works only on workdays still pays for the whole month. Replit does not publish how many deployments can run at once, so 300 sandboxes for your users or 1,000 jobs at once are not confirmed. It also does not document Docker or a disk you can rely on in a published app. On boat, the 1,000-job burst is queued above 90 starts a minute and needs more starts per day than the $2,000 plan allows.

Scenario	boat	Replit
One coding agent, workdays	None that bite	different kind of product: app platform monthly / always-on product: priced as 1 machines kept on and reused
One agent that never stops	None that bite	different kind of product: app platform
50 agents in parallel	None that bite	adjacent product, not a like-for-like sandbox missing persistent disk, Docker inside different kind of product: app platform how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
Sandboxes for your users	None that bite	adjacent product, not a like-for-like sandbox different kind of product: app platform not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)
1,000 short jobs at once	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)	adjacent product, not a like-for-like sandbox different kind of product: app platform not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)

Which one should you use?

Use Replit when

you want Replit Agent to build a web app from a description and host it for you, with databases, sleeping when idle, or regions outside Europe.

An app built and hosted for you. Useful if you want a working app from a description: Replit Agent builds, tests and publishes it for you.
Hosting that costs nothing when idle. Useful for web apps with uneven traffic: Autoscale wakes on the first request and costs nothing while idle.
Regions on five continents. Useful if your users are outside Europe: Replit publishes apps in North America, Europe, Asia, South America and Australia.

Use boat when

your own code needs to start machines for agents: full VMs with Docker and a desktop, coding agents you drive by API, and keys kept outside.

Machines your code creates. An agent platform needs one machine per task or per user, started and stopped by code. On Replit each always-on machine is a published Reserved VM app, and how many can run at once is not published.
Root, Docker and KVM. An agent that runs docker compose, starts a database as a service or boots an Android emulator needs those pieces. On Replit you would have to fit the job into Nix packages or drop it.
Your agents, driven from outside. Replit's MCP server drives Replit Agent only, with no event stream to watch. Its key handling covers AI models, so other API keys sit inside the app as secrets that code the agent runs can read.

Questions people ask

Is boat cheaper than Replit?

For agent machines, yes in most scenarios we priced, mostly because a Replit Reserved VM bills all month. One coding agent on workdays comes to $20 on boat and $122 on Replit, 50 agents in parallel come to $317 versus $1,330, and sandboxes for your users come to $200 versus $403. For 1,000 short jobs at once Replit is lower at $825 against $2,000, but neither fits as is.

Is Replit a sandbox for AI agents?

Not in the usual sense. Replit is an app builder where Replit Agent writes and publishes apps, and its machines are workspaces and published deployments, not sandboxes your code creates by API. boat is built for that second job.

Can I drive Replit Agent from my own code?

Partly. Replit's MCP server lets an MCP client create an app from a prompt, ask Agent questions, start an Agent update and publish, after you sign in with OAuth. It drives Replit Agent only. On boat you prompt, steer and stream events from Claude Code, Codex and other agents inside each sandbox.

Can I run Docker on Replit?

Replit's docs set up environments with Nix packages and do not describe running Docker inside a workspace or a published app. Every boat sandbox is a full VM with root, systemd, Docker and /dev/kvm.

Where does my data run?

boat runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. Replit hosts data mainly on Google Cloud in the United States, and on Core and up you can publish apps in North America, Europe, Asia, South America or Australia.

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. Replit's docs say it has a SOC 2 Type 2 attestation.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial