Integrations
Does it fit the stack you already have?
Moonray AI installs as an app on your code host, connects to the tool your team tracks work in, and runs the change in a preview or staging environment you already operate. It does not ask you to adopt anything new, and it does not create infrastructure.
Where your code lives
Moonray AI installs as an app on your code host. There is nothing to run and nothing to host.
- GitHub Supported
- Cloud and Enterprise Cloud. Install on one repository or all of them. Reviews begin on the next pull request opened.
- GitLab On the way
- Next on the roadmap. Tell us you need it and it moves up, because we prioritise this list by who is asking.
- Bitbucket, Azure DevOps Ask us
- Not supported today. Worth telling us if it is the reason you cannot use us.
Where the work is tracked
The ticket is how we check the change against what was actually asked for, and how we find the matching pull request in another repository.
- Your issue tracker Ask us
- The connection is made at setup. Tell us which tracker your team uses and we will confirm it before you install, rather than list every tool and hope.
- No tracker Supported
- Everything else runs. The intent check is skipped and listed as not checked in the assessment.
Where the change can be run
Runtime evidence needs somewhere to start the change up. We do not create environments, we use one you already have.
- Per pull request preview environments Supported
- The best case. Each change already has its own URL, so the browser session runs against exactly the change under review.
- A shared staging environment Supported
- Works, with the caveat that other people deploying to it while we are running affects attribution, and we will say so when it does.
- Ephemeral environments built in CI Supported
- If your pipeline can stand one up and give us a URL, we can use it.
- No environment Supported
- Everything except the browser evidence still runs, and the assessment states that it was unavailable.
What it reads without being asked
If your team has already written down what good looks like, we would rather read that than ask you to write it again.
- README and contributing guides Supported
- Picked up from the repository at indexing time.
- AI instruction files Supported
- AGENTS.md, CLAUDE.md and the editor and agent rule files your team already keeps.
- Linting and formatting configuration Supported
- Used as a source of your conventions, so findings can cite them by name.
- Your test suite Supported
- Run in an isolated environment against test data, scoped to the part of the suite the change affects.
See it on your own pull requests.
We install on one repository, let Moonray AI assess the next changes your team opens, and go through what it found with you. If the position is not better than what you have now, you will know within a week.
Nothing to host. Reviews begin on the next pull request opened.