GitHub Codespaces

GitHub Codespaces — Devcontainer-backed cloud VMs built for humans, occasionally repurposed for agents. Codespaces gives every repository a full Azure VM configured by a devcontainer, with an editor, port forwarding and persistent storage. It is designed for a developer sitting in front of it, not for an API creating four hundred of them, and the boot times and quotas reflect that. It is in this roster because plenty of teams reach for it first, and because the Australian region and the devcontainer standard are real advantages. Built by GitHub. Founded 2020. Public.

We track it in 1 comparison — Sandbox providers — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 19 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Sydney region — Yes, which only 3 of 16 tools here manage.
• Funding — public, tied for best across 4 of 15 tools.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• Cold start — 45 s, the weakest of the 16 here. Riza records 120 ms.
• MCP server — No. Daytona records Yes.
• Concurrent limit — 10 sandboxes, the weakest of the 13 here. Vercel Sandbox records 2,000 sandboxes.
• Meter — per-minute, 12th of 19. Cloudflare Sandbox records per-10ms.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 25 of 26 tracked fields carry a value for GitHub Codespaces, and 11 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is ascii. GitHub Codespaces is ahead on Custom images (Yes against Partial) and Preview URLs (Yes against Partial). That pattern repeats across the rest of the roster — see GitHub Codespaces alternatives for the other rivals, each compared the same way.

Company

GitHub

Founded

2020

Funding

Public

Fields we track

25 of 26

Last verified

2026-01-15

Included because teams reach for it first and then discover the concurrency limits and minute-scale boots. It is an excellent environment for a human and a bad substrate for an API creating hundreds of sandboxes. The devcontainer spec, though, is the most portable image format on this page.

Cold start

45 s16th of 16

Inferred

MCP server

○No12th of 16

Inferred

Concurrent limit

10 sandboxes13th of 13

Inferred

Price / hour

$0.18 /hr6th of 9

Vendor-claimedverified 2026-01-15source

Sydney region

●Yes1st of 16

Vendor-claimedverified 2026-01-15source

Funding

public1st of 15

Vendor-claimedverified 2026-01-15source

Meter

per-minute12th of 19

Inferred

Isolation

vm1st of 16

Inferred

GitHub Codespaces is the right call in these situations, each one drawn from a field we actually record:

• Human-in-the-loop agent sessions rather than autonomous fleets.
• You need an Australian region and are already on GitHub.
• Your environments are already defined as devcontainers.
• Sydney region is your binding constraint. GitHub Codespaces records Yes, which only 3 of the 16 tools in the Sandbox providers roster do. We define that field as whether sandboxes can be pinned to an Australian region.
• Funding is your binding constraint. GitHub Codespaces records public, the best figure in the Sandbox providers roster. We define that field as latest disclosed funding stage of the company operating the product, as a crude proxy for how long it can keep subsidising compute.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Cold start. GitHub Codespaces records 45 s, the weakest of the 16 tools in the Sandbox providers roster. Riza records 120 ms on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• MCP server. GitHub Codespaces records No on the Sandbox providers table. Daytona records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Concurrent limit. GitHub Codespaces records 10 sandboxes, the weakest of the 13 tools in the Sandbox providers roster. Vercel Sandbox records 2,000 sandboxes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Meter. GitHub Codespaces records per-minute, 12th of 19 in the Sandbox providers roster. Cloudflare Sandbox records per-10ms on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Runtimes. GitHub Codespaces records any-oci-image, 10th of 16 in the Sandbox providers roster. E2B records python, javascript-typescript, bash, any-oci-image on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 1 of the 26 fields we track for GitHub Codespaces are still blank: GitHub stars. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.