Sunup watches the APIs your code depends on. When one changes, it rewrites the affected code, proves it with your tests in a sandbox, and opens a pull request for your team to review.
Animated example: the Sunup agent reads the OpenAI SDK migration guide, finds four outdated lines in app/chat.py, rewrites them, runs 212 tests in a sandbox, and opens pull request number 214.
Illustrative example.
Sunup keeps a live map of the external APIs your code calls. When one of them changes, it already knows which lines are affected and goes to work.
Everything a careful engineer would do for a migration, done the same way every time.
Sunup follows changelogs, SDK releases, and API specs, and matches each change to the exact lines in your code that use it.
Rules handle routine renames. AI handles the rest. Everything else stays as you wrote it.
Your own tests run in an isolated sandbox. If a changed line isn't covered by a test, the pull request says so.
With the reason for the change, the diff, and the test evidence. Review and merge it like any other PR.
The upgrade your team keeps postponing happens while everyone is offline.
Your provider announces a breaking change. Sunup picks it up.
It maps each place in your code that touches the old API.
The new code runs against your own test suite in an isolated sandbox.
You start the day with a change to review, not an outage to fight.
Sunup proposes changes. People decide what ships.
Every change arrives as a pull request and goes through your normal review.
Tests run in a short-lived sandbox with no access to your secrets or production systems.
Each pull request shows which tests ran and which changed lines they covered.
If Sunup isn't confident a change is correct, it tells you instead of opening a pull request.
We're starting with a small group of engineering teams. Leave your email and we'll reach out.