GitLab brings agents to Vertex
GitLab said its Duo Agent Platform can call foundation models through Google’s Vertex AI while enforcing built‑in compliance and audit controls. (finance.yahoo.com) The integration also lets organisations run GitLab’s AI Gateway on Google Cloud without provisioning separate AI infrastructure, framing DevSecOps as a governed environment for agent actions. (itwire.com)
GitLab has wired its Duo Agent Platform into Google Cloud’s Vertex AI, letting software teams run GitLab agents against Google models inside the same development workflow. (about.gitlab.com) GitLab announced the expanded Google Cloud partnership on April 14, 2026. The company said customers can use Vertex AI models they already run on Google Cloud and count that usage against existing Google Cloud spending commitments. (about.gitlab.com) Vertex AI is Google Cloud’s platform for building and serving machine learning systems, including Gemini and other foundation models. GitLab said its agents can now call those models natively while GitLab keeps the work tied to issues, code, merge requests, pipelines, and security findings already stored in its platform. (docs.cloud.google.com ) (about.gitlab.com) GitLab’s pitch is that an “agent” should act more like a junior teammate than a chatbot: it can plan work, draft code, review changes, and help fix security problems across the software development lifecycle. GitLab says Duo Agent Platform has been generally available since January 2026. (docs.gitlab.com) (about.gitlab.com) The new piece is governance. GitLab said enterprises can apply built-in compliance controls, audit trails, and permission boundaries while those agents use Vertex AI models, instead of sending developers to a separate artificial intelligence tool outside the company’s normal software controls. (finance.yahoo.com) (markets.ft.com) GitLab also said organizations can run its artificial intelligence gateway on Google Cloud services such as Google Kubernetes Engine or Cloud Run, whether GitLab manages that gateway or the customer hosts it. That means teams do not need to stand up separate artificial intelligence infrastructure just to connect GitLab agents to models. (markets.financialcontent.com) The timing fits a wider scramble among cloud and software vendors to control how companies discover, govern, and monitor fleets of artificial intelligence agents. Forbes reported on April 10 that major cloud providers are turning agent registries and governance layers into a new competitive front. (forbes.com) Investors treated the announcement as material, at least initially. MarketWatch reported GitLab shares rose about 5% in after-hours trading on April 14 to $21.10 after the company disclosed the expanded Google Cloud collaboration. (marketwatch.com) GitLab is betting that companies buying artificial intelligence for software work want fewer standalone tools and more control inside the systems they already use to ship code. Google Cloud gets another path for Vertex AI adoption, and GitLab gets to sell agents as part of the governed plumbing of enterprise software delivery. (about.gitlab.com 1) (about.gitlab.com 2)