GitHub Codespaces vs Beam

GitHub Codespaces is a dev environment for people: a Linux dev container for a GitHub repository, opened in VS Code or the browser, that stops after 12 hours at most. Beam is a serverless cloud you drive from a Python or TypeScript SDK, with quick gVisor sandboxes, persistent CPU VMs and 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 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.

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

Beam

Beam is a serverless cloud for GPU inference, sandboxes and background jobs, built on its open-source runtime Beta9.

Beam runs functions, REST endpoints, task queues, pods, sandboxes and VMs on CPUs and GPUs, all from a Python or TypeScript SDK. A sandbox is a container isolated with gVisor that starts in a second or two, lives until you terminate it or its time to live runs out, and can be saved as a filesystem image or a memory snapshot. Beam VMs are a separate CPU product: a microVM with its own kernel, systemd and a root disk that stays when it stops. Much of Beam is a GPU serverless platform for AI teams.

Isolation: Sandboxes are containers using runc and gVisor, with an opt-in microVM mode for CPU sandboxes; Beam VMs are CPU microVMs
Infrastructure: Runs on AWS and Google Cloud, in the United States; no other region is listed
GPUs: GPU sandboxes and serverless GPUs, from T4 and RTX 4090 up to H100, H200 and B200 machines
Open source: Beta9 runtime under AGPL-3.0, free to self-host
Bring your own cloud: Management fee per vCPU and GB of RAM, on top of your own cloud bill
Plans: Developer (pay as you go, 30 CPU containers), Team at $89 a month (1,000 CPU containers), Growth by contact
Compliance: SOC 2 Type II; HIPAA BAA for Enterprise customers

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	Beam: 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 needs Docker, systemd and a disk that lasts; Codespaces stops every 12 hours, Beam sandboxes end with their time to live, and neither documents /dev/kvm, which boat has on every machine.	274th of 367, with limits $4,618 a month	69th of 367, with limits $551 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on one machine all month does not fit Codespaces, which stops after 12 hours at most; a Beam VM or a boat sandbox keeps its disk and keeps running.	309th of 366, with limits $6,970 a month	115th of 366, with limits $651 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 Beam fits short code runs well: its sandboxes start in a second or two, bill per second and go away when the timer ends, while each codespace builds a dev container on a new VM.	288th of 345, with limits $619 a month	8th cheapest of 345 $117 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 Codespaces are made for GitHub users on a repository and GitHub does not publish how many can run at once, while Beam and boat both hand out machines to your own users from code.	281st of 361, with limits $1,964 a month	3rd cheapest of 361 $290 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	341st of 360, with limits $939 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	13th cheapest of 364 $251 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 no fork or snapshot API, so each run starts from a repo or a prebuild; Beam can restore memory snapshots, and boat forks a running VM that also has /dev/kvm for Android and VM builds.	314th of 377, with limits $909 a month	12th cheapest of 377 $171 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 at most, while a Beam VM and a boat sandbox both keep running and keep their disk when stopped.	130th of 368, with limits $270 a month	13th cheapest of 368 $21 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 Beam has a graphical desktop, while boat streams a 60fps Linux desktop with Chromium for computer use.	267th of 369, with limits $1,367 a month	111th of 369, with limits $237 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	195th of 367, with limits $176 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	200th of 346, with limits $131 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	42nd of 338, with limits $923 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	175th of 360, with limits $155 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 Beam has GPUs from RTX 4090 up to H100, H200 and B200; current Codespaces machines have no GPU, and boat is CPU only.	Can't run it	Cheapest of 98 $458 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	Beam	boat
Isolation	A Docker container on its own newly built VM, with its own virtual network	gVisor container by default for sandboxes; separate Beam VMs are CPU microVMs with their own kernel	Every sandbox is a 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	Sandbox time to live is 10 minutes by default; set -1 to run until you terminate it	Runs until you stop it; no session cap on paid plans
Files after a stop	Files are kept and storage is billed; stopped codespaces are deleted after 30 days by default	A sandbox ends with its time to live unless you save an image or use a volume; a Beam VM keeps a 50 GiB root disk while stopped	Disk saved every minute and on stop; a stopped sandbox keeps it and costs nothing
Docker and systemd	Docker and sudo inside the dev container	Docker inside sandboxes with docker_enabled; systemd only in Beam VMs, not in sandboxes	Docker, systemd and root, like a normal Ubuntu server
Nested virtualization	/dev/kvm is not documented	/dev/kvm is not documented	Yes, /dev/kvm for Android emulators and VMs
Fork and snapshots	No copy or snapshot endpoint; new codespaces start from a repo, branch, pull request or prebuild	Memory snapshot of a running sandbox with its processes, restored into new sandboxes	Fork a running sandbox with its disk; named snapshots as templates
Starting point	Dev container config in the repository, with prebuilds built by GitHub Actions	A container image you choose, or a saved filesystem image or memory snapshot	Named snapshots (templates), shareable by code; no Dockerfile builds
GPUs	No GPU machine types in current docs	GPU sandboxes and serverless GPUs up to H100, H200 and B200	No, CPU only
Desktop and computer use	VS Code in the browser or on your machine, JupyterLab and a terminal; no graphical desktop	No desktop or browser product	60fps Linux desktop with Chromium, computer use and browser control
Reaching the machine	A URL per forwarded port, private, organization or public; SSH and CLI tunnels; no public IP	A public HTTPS URL per exposed port with no built-in auth; no raw TCP or dedicated IP	HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv4 or IPv6
Outbound internet	Open internet; GitHub says there is no way to restrict it	Block all outbound traffic, or allow up to 10 CIDR ranges, changeable while running	Open internet on every plan; no provider-side allowlist
Coding agents	GitHub Copilot as a VS Code extension; other agents you install and run yourself	None preinstalled; you install and run them through process exec	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping keys out of the machine	Secrets are copied into the codespace as environment variables	Secrets are exposed as environment variables inside the sandbox	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Regions	US East, US West, Europe West and Southeast Asia	US only; no other region is listed	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

Feature	GitHub Codespaces	Beam	boat
Full VM (own kernel)	Yes	No	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	Not published	No	Yes
Desktop GUI	No	No	Yes
Browser	No	No	Yes
Computer-use API	No	No	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	No	No	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	No	Yes	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	No	Yes	Yes
Idle auto-stop	Yes	No	No
Wake on request	No	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	No	No	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	No	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	Yes	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	No	No	Yes
Audit logs	Yes	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	No	Yes	No
EU data residency	Yes	Not published	Yes
Zero data retention	Not published	Not published	Yes

Performance

GitHub CodespacesNot measured

BeamNot measured

boat26.69 runs/s

There is no comparable CPU measurement for GitHub Codespaces or Beam: neither has a result on the StarSling hpc-sandbox-benchmarks test, so we cannot say which is faster at CPU work. boat did 26.69 Node.js build-and-test runs per second on that test at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Beam's own guide says its sandboxes cold-boot in 1 to 3 seconds.

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 Beam 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	Beam, 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	$51 · Personal account: GitHub Free	$5 · Developer	$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	$22 · Developer	$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	$410 · Team	$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	$191 · Team	$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	$259 · Team	$2,000 · $2000/mo · with limits

GitHub Codespaces: Codespaces bills $0.09 per core-hour for the whole time 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 4 vCPU jobs are priced on the 4-core 16 GB machine; personal accounts get a free monthly quota and organizations do not.

Beam: Beam sandboxes bill per second for each CPU core (two vCPU) and each GiB of RAM you request, until you terminate them or their time to live ends, so an idle tail is billed too. Developer has no fee, Team costs $89 a month plus usage with no usage credit, and there are no egress fees.

Beam: Plans start at $20 a month, and the whole fee 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 the always-on price for Codespaces assumes a script that restarts it, and running processes end at each stop. GitHub does not publish how many codespaces can run at once, so 300 user sandboxes and 1,000 short jobs are not confirmed. Beam's Developer plan allows 30 CPU containers at once, so 50 agents need the Team plan, and Beam publishes no price for extra disk, so the scenarios count none. boat's start limits queue the 1,000-job burst, which Beam's Team plan fits.

Scenario	GitHub Codespaces	Beam	boat
One coding agent, workdays	None that bite	disk beyond 0 GiB: price unknown	None that bite
One agent that never stops	Personal account: GitHub Free: sessions capped at 12 h	disk beyond 0 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)	disk beyond 0 GiB: price unknown	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)	disk beyond 0 GiB: price unknown	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)	disk beyond 0 GiB: price unknown	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. For teams on GitHub: open a ready VS Code setup from any repo, branch or pull request, with prebuilds from GitHub Actions.
Free hours for personal accounts. For occasional personal work: a GitHub Free account includes 120 core-hours and 15 GB-month of storage each month.
Regions in the US, EU and Asia. For developers spread around the world: codespaces run in US East, US West, Europe West and Southeast Asia.

Use Beam when

you need GPUs, many short sandboxes that start in seconds, US hosting with outbound rules, or a runtime you can self-host.

GPUs in the same platform. For work that needs a GPU: Beam offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200.
Quick sandboxes for short jobs. For many short code runs: sandboxes start in a second or two, bill per second and end on their own timer.
Open source and your own cloud. For teams that must self-host: the Beta9 runtime is AGPL-3.0, and Beam can also run in your own cloud for a fee.

Where boat fits

Codespaces is built for people editing a repo, and Beam is built around serverless jobs and GPUs. If what you are really running is coding agents that work for hours, install tools, run Docker and need a screen, boat gives each one a full VM built for that. Pick Beam instead when you need GPUs, and Codespaces when your developers want a VS Code box per repo.

Machines that keep running and keep their work

A codespace stops at 12 hours even while in use, so a long agent task needs a restart script and loses its processes. A Beam sandbox ends with its time to live unless you save an image. boat runs until you stop it and saves the disk every minute.

A full VM with systemd and /dev/kvm

A codespace is a dev container and a Beam sandbox is a gVisor container without systemd; neither documents /dev/kvm, so Android emulators and nested VMs have nothing to start on. Every boat sandbox has its own kernel, systemd, Docker and /dev/kvm.

Agents, desktop and keys built in

On both, you install and drive each agent yourself, there is no desktop for computer use, and API keys sit in environment variables any code can read. boat ships agents with a prompt API, a 60fps desktop, and keeps keys outside in a proxy.

Use boat when your code starts and drives agents that work for hours or days: full VMs with systemd and /dev/kvm, a desktop and open ports, built-in coding agents with keys kept outside, and a disk that is still there the next time it starts. Compare it one to one: boat vs GitHub Codespaces and boat vs Beam.

Questions people ask

Is GitHub Codespaces cheaper than Beam?

No, Beam costs less in all five scenarios we priced. One coding agent on workdays is $51 a month on Codespaces against $5 on Beam, and 50 agents in parallel come to $3,019 against $410. Beam publishes no price for extra disk, so its figures count none, and boat sits close to Beam, at $20 and $317 for those two.

Which is faster, Codespaces or Beam?

We cannot say for CPU work: neither has a result on the StarSling benchmark we use. Beam's guide says its sandboxes cold-boot in 1 to 3 seconds, while a codespace builds a dev container on a new VM, which prebuilds speed up. boat did 26.69 runs per second on that benchmark.

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

Not on Codespaces without restarts: a codespace stops after 12 hours at most, even while in use. On Beam you can set a sandbox's time to live to -1 so it runs until you terminate it, or use a Beam VM that keeps its disk. A boat sandbox runs until you stop it, with no session cap on paid plans.

Can Codespaces and Beam run Docker?

Yes. Docker works inside a codespace's dev container with sudo, and Beam supports Docker inside a sandbox with docker_enabled. Neither documents /dev/kvm, which every boat machine has along with Docker and systemd.

Do Codespaces or Beam have GPUs?

Beam does, with GPU sandboxes and serverless GPUs up to H100, H200 and B200. Current Codespaces docs list no GPU machine types, and boat is CPU only, so pick Beam for GPU work.

Where do Codespaces and Beam run?

Codespaces runs in US East, US West, Europe West and Southeast Asia, and you pick the region when you create one. Beam runs on AWS and Google Cloud in the United States, with no other region listed. boat runs only in the EU, in Germany, Finland and France.

Try boat

Install the CLI, then run boat new.

7-day free trial