GitHub Codespaces vs an agent sandbox which one should run AI agents?

Which should you use, GitHub Codespaces or an agent sandbox?

It depends on who drives the machine, a person or a program. For programs, such as an agent that needs a fresh machine per task, Runtime offers that kind: $0.03125 an hour while a 2 vCPU, 4 GiB sandbox waits, and $0.08 when busy. That is below a 2-core codespace's hourly rate. Commands return structured results. Pick Codespaces for people: a developer, a class or a reviewer who wants a ready editor for a repository, inside GitHub's billing and its free monthly hours.

What Codespaces is built for

GitHub describes a codespace as a development environment for a repository. When you create one, "a virtual machine (VM) is created", "dedicated and private to you", and "GitHub Codespaces uses a Docker container as the development environment". You connect to it with an editor, or from a terminal with gh codespace ssh.

• Files. /workspaces is "a persistent directory that is mounted into the container". Changes elsewhere survive a stop and start but "are not preserved when you rebuild the container".
• Idle timeout. "By default this period is 30 minutes", and it can be set from 5 to 240 minutes.
• Retention. Stopped codespaces are deleted after 30 days inactive by default, and 30 days is the maximum.
• API. The REST API creates a codespace in a repository and starts and stops it (POST /repos/{owner}/{repo}/codespaces, POST /user/codespaces/{codespace_name}/start). Commands inside run over a connection such as gh codespace ssh.

Side by side

What each costs

GitHub's rates, checked 26 October 2026: compute from $0.18 an hour on a 2-core machine to $2.88 on 32 cores, "proportional to the number of processor cores", and storage at $0.07 per GB-month. A personal account on GitHub Free includes 120 core hours of compute, 60 hours on a 2-core machine, and 15 GB-month of storage a month. GitHub Pro includes 180 core hours and 20 GB-month.

Runtime at 2 vCPU and 4 GiB: $0.03125 an hour waiting (memory plus a CPU floor of a twentieth of a vCPU) and $0.08 an hour with both CPUs busy.

Most of an hour, an agent waits on its model. Measured CPU bills that wait at the floor, not for two idle cores (pricing).

The Runtime equivalent

A named environment per task or per user. It is found again if it exists, paused after 15 quiet minutes, and woken by the next command.

TypeScriptimport { Sandbox } from "withruntime";const dev = await Sandbox.getOrCreate("issue-4821", { idlePauseSeconds: 900 });await dev.exec("git clone https://github.com/octocat/Hello-World.git repo || true", {  timeoutMs: 120_000,});const run = await dev.exec("cd repo && git log --oneline -1");console.log(run.stdout);

Pythonfrom withruntime import Sandboxdev = Sandbox.get_or_create("issue-4821", idle_pause_seconds=900)dev.exec("git clone https://github.com/octocat/Hello-World.git repo || true", timeout_ms=120_000)print(dev.exec("cd repo && git log --oneline -1").stdout)

To look over the agent's shoulder in your own editor:

Terminalruntime sandboxes ssh config --install   # then connect VS Code to issue-4821.runtime

Which one fits

• Pick Codespaces for people: a developer, a class or a reviewer who wants a ready editor for a repository, inside GitHub's billing and its free monthly hours.
• Pick an agent sandbox for programs: an agent that needs a fresh machine per task, a hundred at the same time, commands with structured results, network rules it cannot change, keys it never holds, and a bill that stays small while it waits on the model.

More: coding agent sandbox, per-user dev environments, pause and resume a sandbox, SSH and editors.

Sources

Checked 26 October 2026.

• GitHub: Codespaces billing and GitHub's plans
• GitHub: Codespaces deep dive
• GitHub: timeout period and automatic deletion
• GitHub: Codespaces REST API, gh codespace ssh
• Runtime pricing, speed and SSH and editors

Facts on this page were checked on 26 October 2026.