GitHub Codespaces vs Koyeb

GitHub Codespaces is a dev environment for people: a container on its own VM, opened from a GitHub repository in VS Code, that stops after 12 hours at most. Koyeb is a sandbox you drive from code: a microVM from any Docker image that can sleep when idle, wake on a request, and run on GPUs.

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 bochka: 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.

Isolation: A Docker container on its own newly built VM, with its own virtual network
Operating system: Linux only; Windows and macOS are not supported for the remote container
Machine sizes: 2, 4, 8, 16 or 32 cores, with 4 GB of memory per core
Lifetime: Stops after 30 idle minutes by default (5 to 240), and after 12 hours at most even while in use
Regions: US East, US West, Europe West and Southeast Asia
Free usage: Personal Free accounts get 120 core-hours and 15 GB-month a month, Pro 180 and 20; organizations get no free quota
Compliance: GitHub Enterprise Cloud lists SOC 1, SOC 2 and SOC 3 reports and ISO 27001

Koyeb

Koyeb is a serverless cloud for apps, inference and sandboxes, and in February 2026 it agreed to join Mistral AI.

A Koyeb sandbox is a Koyeb service: a microVM started from any Docker image and driven from Python or JavaScript SDKs that run commands, read files and expose a port. It can scale to zero when idle and wake on the next request, and it can run on CPU or GPU instance types. It is built for teams that run AI agents or untrusted code next to apps they already host on Koyeb.

Isolation: MicroVM per instance
Company: Agreed to join Mistral AI (announced February 17, 2026); the platform keeps running and becomes part of Mistral Compute
Regions: Frankfurt, Paris, Washington D.C., AWS US East, Singapore, Tokyo, plus San Francisco in preview
CPU share: At least 0.25 dedicated vCPU per GB of memory, bursting to all cores
Your own infrastructure: Edge and on-premise deployments for Enterprise, on request
Compliance: ISO 27001 and SOC 2 listed on the Enterprise plan

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 workload	GitHub Codespaces: price rank	Koyeb: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Codespaces stops a long build-and-test agent at 12 hours and Koyeb's local disk is lost on redeploy, while bochka keeps a full VM with Docker and its disk running.	274th of 367, with limits $4,618 a month	54th of 367, with limits $366 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 hits the 12-hour stop on Codespaces and loses its VM in a Koyeb deep sleep, while a bochka sandbox keeps running and keeps its files.	309th of 366, with limits $6,970 a month	135th of 366, with limits $923 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 Koyeb fits short code runs well, with small instances that sleep after 5 idle minutes and wake on the next request; each codespace builds a dev container on a new VM.	288th of 345, with limits $619 a month	4th cheapest of 345 $66 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 Koyeb is built to hand sandboxes to your own users from an SDK, while Codespaces are created for GitHub users on a repository and GitHub does not publish how many can run at once.	281st of 361, with limits $1,964 a month	6th cheapest of 361 $495 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	237th of 360, with limits $1,631 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	19th cheapest of 364 $429 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 Neither documents /dev/kvm for Android or VM image builds, and Codespaces has no copy of a warm machine; bochka exposes /dev/kvm and forks a running sandbox.	314th of 377, with limits $909 a month	142nd of 377, with limits $88 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Codespaces is a polished VS Code box per repo but stops after 12 hours; Koyeb sandboxes have no SSH and lose local disk on redeploy; bochka is a full VM that keeps running.	130th of 368, with limits $270 a month	217th of 368, with limits $37 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 Neither Codespaces nor Koyeb gives the sandbox a graphical desktop, while bochka streams a 60fps desktop with Chromium for computer use.	267th of 369, with limits $1,367 a month	81st of 369, with limits $123 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	172nd of 367, with limits $123 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	172nd of 346, with limits $89 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	65th of 338, with limits $1,683 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	267th of 360, with limits $445 a month	233rd of 360, with limits $299 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 Koyeb runs GPU instances up to H100 and H200, while Codespaces has no GPU machine types in its current docs and bochka has no GPUs.	Can't run it	3rd cheapest of 98 $628 a month	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	Can't run it

Key features

Feature	GitHub Codespaces	Koyeb	bochka
What it is	A cloud dev environment for a GitHub repository, opened in VS Code, the browser or the GitHub CLI	A sandbox service started from any Docker image and driven from Python or JavaScript SDKs	A sandbox you drive from code, with an API and SDK on every plan
Isolation	A Docker container on its own newly built VM, with its own virtual network	MicroVM per instance	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
How long it runs	Stops after 30 idle minutes by default (up to 240) and after 12 hours at most, even while in use	No forced session cap; optional auto-delete timers you set yourself	Runs until you stop it; no session cap on paid plans
Files after a stop	Saved files are kept and storage is billed; stopped codespaces are deleted after 30 days by default	Local disk is lost on redeploy and a deep sleep discards the VM; volumes (preview, 1 to 10 GB) persist	Disk kept across stops and saved every minute; a stopped sandbox costs nothing
Sleep and wake	Stops when idle; you restart it yourself	Scales to zero after 5 idle minutes and wakes on the next request; Light Sleep wakes in about 200 ms	Stop and start by API
Fork and snapshots	No copy or snapshot endpoint; new codespaces start from a repo, branch, pull request or prebuild	SDK snapshots of the filesystem or with running processes, and new sandboxes from them (experimental)	Fork a running sandbox with its files; named snapshots as templates
Docker and nested virtualization	Docker and sudo in the dev container; /dev/kvm not documented	Runs Docker images; nested virtualization not documented	Docker, root, systemd and /dev/kvm on every machine
Desktop and computer use	VS Code, JupyterLab and a terminal; no graphical desktop	No desktop or browser in the sandbox SDK	60fps desktop with Chromium, computer use and browser control
Reaching the sandbox	A URL per forwarded port, private, organization or public; SSH; no public IP	One exposed HTTPS port at a time, plus an optional TCP proxy to one port; no dedicated IP	HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv4 or IPv6
Outbound rules	Open internet; GitHub says there is no way to restrict it	Block all outbound traffic, or allow only listed IPs and CIDRs	Open internet, no provider-side allowlist
Coding agents	GitHub Copilot as a VS Code extension; other agents you install yourself	Tutorials that run agents through the command API; an MCP server lets agents manage Koyeb	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandbox	Secrets are copied into the codespace as environment variables	Secrets are set as environment variables inside the service	Credentials proxy for model providers and any HTTPS API; switch to another account when credits run out
GPUs	No GPU machine types in current docs	RTX 4000 SFF Ada up to H100, H200 and multi-GPU	No
Regions	US East, US West, Europe West and Southeast Asia	Frankfurt, Paris, Washington D.C., AWS US East, Singapore, Tokyo	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

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

Performance

GitHub CodespacesNot measured

KoyebNot measured

bochka26.69 runs/s

There is no comparable measurement for GitHub Codespaces or Koyeb: neither was in the public benchmark runs we use. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Koyeb publishes a CPU share of at least 0.25 dedicated vCPU per GB of memory, bursting to all cores, so its speed depends on how busy the host is.

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 Koyeb 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	GitHub Codespaces, a month	Koyeb, a month	bochka, 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	$29 · Pro	$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	$57 · Pro	$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	$475 · Pro	$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	$329 · Scale	$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	$485 · Scale · 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; personal accounts get a free monthly quota and organizations do not.

Koyeb: Koyeb bills each instance per second at a fixed price per instance type, and Deep Sleep costs nothing. Pro costs $29 a month with $10 of usage included and Scale $299 a month with $100 included; the rest of the fee is not credit.

Koyeb: Plans start at $20 a month, and the whole fee is 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, and GitHub does not publish how many can run at once, so 300 user sandboxes and 1,000 short jobs show as not confirmed. Koyeb's priced eco-xlarge shape has a 20 GiB disk with no published price for more, and eco instances guarantee only half of each vCPU, which throttles the 1,000-job burst. bochka's $2,000 plan queues starts above 90 a minute, so none of the three fits that burst as priced.

Scenario	GitHub Codespaces	Koyeb	bochka
One coding agent, workdays	None that bite	disk beyond 20 GiB: price unknown	None that bite
One agent that never stops	Personal account: GitHub Free: sessions capped at 12 h	disk beyond 20 GiB: price unknown	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)	None that bite	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)	None that bite	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)	burstable CPU: 50% of each vCPU guaranteed, throttled above that	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 for a GitHub repository, opened from a branch or pull request, in the US, EU or Asia.

Built into GitHub. Useful if your team lives on GitHub: open a ready codespace from any repo, branch or pull request in VS Code.
Same setup for every developer. Dev container configs and prebuilds built by GitHub Actions give every contributor the same ready machine.
Free hours for personal accounts. A GitHub Free account includes 120 core-hours and 15 GB-month of storage each month, enough for light personal work.

Use Koyeb when

your app hands out sandboxes that sleep most of the time and wake on a request, need GPUs, or must run in the US or Asia.

Sandboxes you drive from code. Useful for apps that hand out sandboxes: an SDK runs commands, reads files and exposes a port on each microVM.
Sleep when idle, wake on request. Good for sandboxes that sit idle between requests: they scale to zero and wake on the next one.
GPUs and egress rules. Useful when a job needs a GPU or locked-down network: GPUs up to H100 and H200, and outbound IP allowlists.

Where bochka fits

If what you are really running is coding agents that work for hours, Codespaces stops them at 12 hours and Koyeb throws away their disk on a deep sleep. bochka gives each agent a full VM that keeps running and keeps its files, with agents, a desktop and hosting built in.

Machines that keep running and keep their work

A codespace stops at 12 hours even while in use, so you need a restart script, and its processes end. On Koyeb lasting files need a preview volume of 1 to 10 GB. bochka runs until you stop it and saves its disk every minute.

A full VM with /dev/kvm, a desktop and open ports

Neither documents /dev/kvm, so Android emulators and microVMs must run elsewhere, and neither has a desktop for computer use. Koyeb exposes one HTTPS port at a time. bochka has /dev/kvm, a 60fps desktop and HTTPS on up to 50 ports.

Coding agents you drive from outside, keys kept out

On both you build the harness yourself, over SSH or the exec API, and API keys sit in environment variables the agent can read. bochka preinstalls Claude Code, Codex and others with a prompt, steer and events API and a credentials proxy.

Use bochka when your code starts and drives agents that work for hours or days: full VMs with /dev/kvm, a desktop and open ports, built-in coding agents with keys kept outside, and machines that keep their disk and fork while running. Compare it one to one: bochka vs GitHub Codespaces and bochka vs Koyeb.

Questions people ask

Is GitHub Codespaces cheaper than Koyeb?

Not in the scenarios we priced. One coding agent on workdays is $51 a month on Codespaces against $29 on Koyeb and $20 on bochka, and 50 agents in parallel come to $3,019 against $475 and $317. For 1,000 short jobs at once, none of the three fits as priced.

Which is faster, GitHub Codespaces or Koyeb?

We have no comparable CPU measurement for either, so we cannot rank them. bochka did 26.69 runs per second on the Node.js build-and-test benchmark at 4 vCPU / 8 GB. Koyeb guarantees at least 0.25 dedicated vCPU per GB of memory and bursts above that.

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

Not on Codespaces without restarts: every codespace stops after 12 hours, even while in use. Koyeb has no forced session cap, but its local disk is lost on redeploy and a deep sleep discards the VM. A bochka sandbox runs until you stop it and keeps its disk.

Can GitHub Codespaces and Koyeb run Docker?

Docker works inside a codespace through dev container features, and Koyeb sandboxes start from any Docker image. Neither documents /dev/kvm, so Android emulators and microVMs are not a supported setup. Every bochka machine has Docker, systemd and /dev/kvm.

Do Codespaces or Koyeb have GPUs?

Koyeb runs instances from an RTX 4000 SFF Ada up to H100 and H200, billed per second. Codespaces lists no GPU machine types in its current docs, and bochka is CPU only.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview