Developer Tools
runspace
Last updated 2026-10-22 · benchmark checked 2026-11-08 · unchanged since 2026-10-22 — deterministic & reproducible
Disposable cloud sandboxes for running commands without touching your host machine.
runspace at a glance
Runspace is a command-line tool and MCP server that runs commands, scripts, and build tasks inside temporary GitHub Codespaces, returning the output and a patch of changes without touching the user's own machine, for developers, DevOps engineers, and AI agents.
Good for
- Running build scripts, tests, or formatting tools in an isolated environment instead of on your local machine
- Letting an AI agent execute commands against a repository through the same tool set used by human developers, without giving it access to your host
- Getting back a patch of exactly what changed in a sandbox run, which you can review and apply yourself
Questions people ask
What does Runspace actually do with my commands?
It creates a temporary GitHub Codespace tagged 'runspace', runs the command there over SSH through a Dev Tunnel, and returns the output, exit codes, and a patch of all changes since the sandbox was created, then deletes the sandbox.
Do I need to install anything complicated?
No, it installs as a single static binary via a shell script (Linux/macOS) or PowerShell script (Windows), which also verifies the download against SHA-256 checksums.
Can AI agents use Runspace the same way I do?
Yes, the CLI and the MCP server run the same seven commands with the same input and error handling, so a command that works at your terminal works for an agent.
What does Runspace need access to?
It needs a GitHub token with the codespace scope, kept in the RUNSPACE_TOKEN environment variable; your host runs only the runspace binary and holds no repository configuration.
Does Runspace leave anything behind on my machine or affect my other codespaces?
No, it leaves no daemon or local state after a sandbox is deleted, and it only acts on codespaces whose display name is 'runspace', so it never touches your other codespaces.
Written by Legit.Show from runspace.sandbox.ec on 2026-10-24. It does not change the score.
Are you the maker of runspace? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/runspace-sandbox-ec/2026-11-08. That address never changes; this page moves with every re-measure.
Legit.Show scored runspace 68/100 on 2026-11-08, measured across all 7 frames from its public surface. legit.show/s/runspace-sandbox-ec/2026-11-08
Is runspace production-ready?
Legit.Show scores runspace 68 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on runspace (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 99/100
- Accessibility — 94/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 92/100
- Standards — 92/100
- Discoverability — 47/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 613 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
Developers · AI agents · DevOps engineers · Teams using GitHub
Sources and updates
- Description
- Taken from runspace.sandbox.ec's own website on 2026-10-22.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-08.
Put together from public information, without runspace's involvement. If anything here is wrong, tell us and a person will check it.
Visit runspace → · Alternatives to runspace → · How this was measured →