GitLab now allows Google Cloud customers to “power” GitLab Duo Agent Platform with the Vertex AI models they already use and count that usage towards their existing Google Cloud commitments.
Agents in GitLab Duo Agent Platform can now call Vertex AI models on Google Cloud natively, giving joint customers the model performance they expect with the governance GitLab already provides, the company claimed.
The Vertex AI Model Garden gives joint customers a choice of foundation models, including Gemini, so teams can select models based on performance, cost, or regulatory requirements.
For self-hosted customers, GitLab's Bring Your Own Model option lets teams connect their approved models and gateways.
GitLab's AI Gateway, whether GitLab-managed or self-hosted, runs on Google Cloud runtimes like GKE or Cloud Run, keeping AI workloads on the infrastructure teams already manage.
“AI agents are only as good as the context they operate on and the governance around them,” said Manav Khurana, chief product and marketing officer at GitLab.
“GitLab is where that context lives across issues, code, pipelines, security findings, and this partnership connects it to Vertex AI's strongest models. As agents take on more of the software lifecycle, the platform that provides both the context and the controls becomes the critical layer.”




