Skip to content
Vibedata

Live sandbox

Run it on a real stack

A hosted environment seeded on DuckDB. Author a pipeline, watch it fail a gate, and ship it once it passes. Sign-in goes through GitHub.

The sandbox contains seeded data and an author-to-gate-to-ship loop.

The sandbox runs on our infrastructure, on data we seed. It covers the inner loop: say what you want, the agent authors the pipeline, and a gate decides whether it ships.

Watch the demo

Tell us what you run

Your answers shape where we suggest you start; GitHub sign-in opens the sandbox

Shared environment Use the sample data we seed. Do not put production, personal or confidential data into the sandbox: content you put in may be visible to our staff and, depending on configuration, to other users. The Sandbox Terms and the privacy policy set this out in full.

Vibedata signs you in through GitHub and commits its work to a repository of your own. Sign-in fails if the account's primary email address is not verified.

Restoring the demo places the repository inside that organization, not your personal account. If you don't have one, creating one is free.

Would you rather deploy from your cloud?

Two ways to run it: the hosted sandbox on seeded data, or your cloud marketplace in your own subscription
Deploy from Your Cloud MarketplaceRead how it works