GitHub Codespaces vs Replit

GitHub Codespaces gives a developer a ready Linux dev container for a GitHub repository, in VS Code or the browser, that stops after 12 hours at most. Replit is an AI app builder: you describe an app, Replit Agent writes it, and Replit hosts it.

The companies and products

GitHub Codespaces

GitHub Codespaces is GitHub's cloud development environment: a ready-to-code Linux machine for a repository, opened in the browser, VS Code or the GitHub CLI.

Codespaces is a different kind of product from boat: a dev environment for people working on a GitHub repository, not a sandbox API for agents. Each codespace is a Docker container built from the repo's dev container config, running on its own newly built VM on Azure, with 2 to 32 cores. It is built for developers and teams who want every contributor to start from the same setup, with prebuilds, port forwarding and GitHub billing.

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.

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. “274th cheapest of 367” means 273 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 workloadGitHub Codespaces: price rankReplit: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Codespaces gives an agent Docker in a dev container but stops it at 12 hours, Replit has no API to start many machines, and boat runs full VMs your code creates and forks.
274th of 367, with limits
$4,618 a month
181st of 367, with limits
$2,000 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An always-on assistant needs a Reserved VM on Replit, one published app billed all month, while a codespace stops after 12 hours and must be restarted.
309th of 366, with limits
$6,970 a month
202nd of 366, with limits
$2,033 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
Neither is built for one-minute runs: a codespace builds a dev container on a new VM, and Replit's Autoscale is a web host that wakes on requests, not a code runner.
288th of 345, with limits
$619 a month
228th of 345, with limits
$146 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
Neither GitHub nor Replit publishes how many machines can run at once, so handing 300 sandboxes to your own users is not confirmed on either.
281st of 361, with limits
$1,964 a month
233rd of 361, with limits
$825 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
282nd of 360, with limits
$9,489 a month
258th of 360, with limits
$4,226 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
295th of 364, with limits
$1,519 a month
265th of 364, with limits
$685 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
Codespaces has Docker for container builds but no fork or snapshot API, and Replit's Nix-based environments do not document Docker at all.
314th of 377, with limits
$909 a month
275th of 377, with limits
$425 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
For a box you code in by hand, Codespaces gives a polished VS Code setup per repo and Replit a browser workspace, but only boat keeps running past 12 hours with Docker and systemd.
130th of 368, with limits
$270 a month
165th of 368, with limits
$109 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
A codespace has no graphical desktop, and Replit's VNC pane shows a desktop to a person with no API for an agent, while boat streams a 60fps desktop with Chromium.
267th of 369, with limits
$1,367 a month
190th of 369, with limits
$619 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
275th of 367, with limits
$678 a month
229th of 367, with limits
$317 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
310th of 346, with limits
$922 a month
234th of 346, with limits
$217 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
280th of 338, with limits
$18,637 a month
150th of 338, with limits
$4,378 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
boat can fork one prepared machine into many while it runs; on Codespaces every copy starts again from the repository, and Replit has no API to start many machines.
267th of 360, with limits
$445 a month
208th of 360, with limits
$215 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 itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureGitHub CodespacesReplitboat
Kind of productCloud dev environment for a GitHub repository, opened in VS Code, the browser or the GitHub CLIAI app builder with browser workspaces and app hostingSandboxes you create, stop and fork by API, SDK or CLI
IsolationA Docker container on its own newly built VM, with its own virtual networkNot documented; the security page says strong logical separation between usersEvery sandbox is a full VM with its own kernel
How long it runsStops after 30 idle minutes by default (up to 240) and after 12 hours at most, even while in useA Reserved VM runs continuously; Autoscale goes idle after 15 minutes without requestsRuns until you stop it; no session cap on paid plans
Docker and nested virtualizationDocker and sudo inside the dev container; /dev/kvm and nested virtualization are not documentedSystem packages come from Nix; the docs do not describe Docker, systemd or /dev/kvmDocker, root, systemd and /dev/kvm on every machine
Desktop and computer useVS Code in the browser or on your machine, JupyterLab and a terminal; no graphical desktopVNC pane that streams a native desktop to your browser; no computer-use API60fps desktop and Chromium, computer use and browser control, embeddable stream
Files over timeSaved files are kept and storage is billed; stopped codespaces are deleted after 30 days by defaultWorkspace files and Agent checkpoints at milestones; published apps should not rely on their filesystemSnapshots every minute and on stop; a stopped sandbox keeps its disk and costs nothing
Copying a running machineNo copy or snapshot endpoint; new codespaces start from a repo, branch, pull request or prebuildNo fork of a running machineFork a running sandbox into copies with its files; named snapshots as templates
Driving it from codeREST API and GitHub CLI to create, start, stop and delete; commands run over SSHMCP server tools to create, update and publish apps; no API to start many machinesAPI, SDK and CLI to create, stop, resume, fork and run commands, on every plan
Coding agentsGitHub Copilot as a VS Code extension; other agents you install and run yourselfReplit Agent, which you can also drive from an MCP client (create, update, ask, publish)Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping keys out of the sandboxSecrets are copied into the codespace as environment variablesReplit manages keys for OpenAI, Anthropic, Google and OpenRouter models; other keys are secrets in the appAI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out
Reaching the machineA URL per forwarded port, private, organization or public; SSH and CLI tunnels; no public IPPublished apps on HTTPS domains, custom domains and private deployments; SSH into the workspace on paid plansHTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4; SSH
Starting pointDev container config in the repository, with prebuilds built by GitHub ActionsA chat description that Replit Agent turns into a project, with Nix packagesNamed snapshots (templates), shareable by code; no Dockerfile builds
Hosting a finished appForwarded ports only while the codespace runs, which is 12 hours at mostAutoscale, Static, Scheduled or Reserved VM deployments, with Postgres and App Storage built inHTTPS on running sandboxes; no wake on request and no hosted databases
RegionsUS East, US West, Europe West and Southeast AsiaPublished apps in North America, Europe, Asia, South America and Australia on Core and up; data hosted mainly in the USEU only: Germany, Finland, France
Every feature Battleships tracks (43)
FeatureGitHub CodespacesReplitboat
Full VM (own kernel)YesYesYes
Docker insideYesNoYes
Nested virtualizationNoNoYes
RootYesNot publishedYes
SystemdNot publishedNoYes
Desktop GUINoYesYes
BrowserNoNoYes
Computer-use APINoNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesNoYes
Automatic snapshotsNoYesYes
Fork/cloneNoYesYes
Live fork (no pause)NoNoYes
Memory forkNoNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsNoYesYes
Idle auto-stopYesYesNo
Wake on requestNoYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNot publishedYes
Public IPv4NoNoNo
Egress allowlistNoNoNo
Secret proxyNoYesYes
Secret proxy for any APINoNoYes
Preinstalled agentsNoYesYes
Agent harness APINoYesYes
MCP serverNoYesNo
GPUNoNoNo
WindowsNoNoNo
Arm64NoNot publishedNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsYesYesYes
Usage per sandbox (API)NoYesYes
Audit logsYesYesNo
SSOYesYesNo
SOC 2YesYesNo
HIPAANoNoNo
EU data residencyYesYesYes
Zero data retentionNot publishedNot publishedYes

Performance

GitHub CodespacesNot measured
ReplitNot measured
boat26.69 runs/s

There is no comparable measurement for GitHub Codespaces or Replit: neither was in the public benchmark runs we use, so we cannot say which of the two is faster. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run of 2026-09-29, on dedicated AMD Ryzen 9 9950X hosts.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. GitHub Codespaces and Replit 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.

ScenarioGitHub Codespaces, a monthReplit, a monthboat, 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
$51 · Personal account: GitHub Free$122 · Pro $100 (annual) · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$270 · Personal account: GitHub Free · with limits$122 · Pro $100 (annual) · with limits$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
$3,019 · Personal account: GitHub Free$1,330 · Pro $1,000 (annual) · with limits$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
$850 · Personal account: GitHub Free · with limits$403 · Pro $250 (annual) · 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
$1,889 · Personal account: GitHub Free · with limits$825 · Pro $1,000 (annual) · with limits$2,000 · $2000/mo · with limits

GitHub Codespaces: Codespaces bills $0.09 per core-hour while a codespace is active, plus $0.07 per GB-month for storage while it exists, stopped too. There is no 4-core machine with 8 GB, so a 4 vCPU / 8 GB job is priced on the 4-core 16 GB machine, and personal accounts get a free monthly quota while organizations do not.

Replit: Replit plans (Core $20, Pro from $100) turn into monthly credits for Agent work and hosting, then usage goes on to pay-as-you-go. A Reserved VM has a fixed monthly price per size and bills whether busy or idle, so our prices treat each agent as a Reserved VM kept on all month and leave out Agent usage.

Replit: 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.

Limits in those scenarios

Every codespace stops after 12 hours at most, so it does not fit the always-on scenario: its price there assumes a restart script, and running processes end at each stop. Replit is marked as not a fit in every scenario because it is an app platform: 50 agents means 50 published Reserved VM apps, with no documented Docker or persistent disk inside. Neither GitHub nor Replit publishes how many machines can run at once, so 300 user sandboxes and 1,000 short jobs are not confirmed on either. 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.

ScenarioGitHub CodespacesReplitboat
One coding agent, workdaysNone that bite
  • different kind of product: app platform
  • monthly / always-on product: priced as 1 machines kept on and reused
None that bite
One agent that never stops
  • Personal account: GitHub Free: sessions capped at 12 h
  • different kind of product: app platform
None that bite
50 agents in parallel
  • how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
  • 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)
None that bite
Sandboxes for your users
  • not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)
  • 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)
None that bite
1,000 short jobs at once
  • not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)
  • 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)
  • 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 GitHub Codespaces when

your developers want a ready VS Code environment with Docker for a GitHub repository, opened from a branch or pull request, for sessions under 12 hours.

  • Built into GitHub. Useful if your team lives on GitHub: open a codespace from any repo, branch or pull request, with the dev container already set up.
  • Docker inside the dev container. Useful if your project builds or runs containers: a codespace has Docker and sudo, which Replit's docs do not describe.
  • Free hours for personal accounts. Useful for occasional personal work: a GitHub Free account includes 120 core-hours and 15 GB-month of storage each month.

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 with Postgres and storage.
  • Hosting that costs nothing when idle. Useful for web apps with uneven traffic: Autoscale wakes on the first request and costs nothing while idle.
  • An always-on machine with no 12-hour stop. Useful for one app that must stay up: a Reserved VM runs continuously, while a codespace stops after 12 hours.

Where boat fits

Codespaces is built for a developer working on a repository, and Replit for a person who wants an app built and hosted. If what you are really running is agents that your own code starts, steers and stops, neither was made for it. boat gives each agent a full VM by API that keeps running, keeps its work and forks while it runs.

Machines that run as long as the job

A codespace stops after 12 hours even while in use, so a long agent task needs a restart script and loses its processes. On Replit the only machine that stays on is a Reserved VM, one published app billed all month.

A full VM with Docker, /dev/kvm and a desktop

Codespaces has Docker but documents no /dev/kvm and no desktop. Replit documents neither Docker nor systemd, and its VNC pane is for a person. Agents that boot emulators, run compose stacks or use a screen get stuck on both.

Your agents, driven from outside with keys kept out

On Codespaces you write the code that starts and watches each agent over SSH, with keys as environment variables. Replit's MCP server drives only Replit Agent, with no event stream. boat ships Claude Code, Codex and more with a prompt, steer and events API.

Use boat when your own code starts and drives agents that work for hours or days: full VMs with Docker, /dev/kvm and a desktop, coding agents you steer by API with keys kept outside, and machines that fork while running. Compare it one to one: boat vs GitHub Codespaces and boat vs Replit.

Questions people ask

Is GitHub Codespaces cheaper than Replit?

It depends on how long the machine runs. One coding agent on workdays costs $51 a month on Codespaces against $122 on Replit, because a Replit Reserved VM bills all month. For one agent that never stops, Replit is $122 against $270 on Codespaces, and boat is $26 a month for the same job.

Which is faster, Codespaces or Replit?

We cannot say: neither is in the public CPU benchmark we use. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in that benchmark.

Can GitHub Codespaces or Replit run Docker?

Codespaces can: Docker works inside the dev container and you have sudo, though /dev/kvm is not documented. Replit's docs set up environments with Nix packages and do not describe Docker. Every boat sandbox has Docker, systemd and /dev/kvm.

Can I run an AI agent 24/7 on Codespaces or Replit?

On Codespaces, not without restarts: a codespace stops after 12 hours even while in use. On Replit, a Reserved VM runs continuously, but it is one published app billed all month. A boat sandbox runs until you stop it, with no session cap on paid plans.

Where does my data run?

Codespaces runs in US East, US West, Europe West and Southeast Asia. Replit hosts data mainly on Google Cloud in the United States and publishes apps on five continents on Core and up. boat runs only in the EU, in Germany, Finland and France.

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

More comparisons