GitLab expands Google Cloud partnership for Vertex AI

GitLab has expanded its partnership with Google Cloud, allowing customers to use Vertex AI models with the GitLab Duo Agent Platform.

According to the companies, customers can count that usage towards their existing Google Cloud spending commitments.

The integration enables AI agents in GitLab Duo Agent Platform to call foundation models through Vertex AI, including Gemini models, from within GitLab. Those agent actions remain subject to GitLab's compliance controls and audit logging.

The move connects GitLab's software development and security workflow tools with Google Cloud's managed AI model service. It is aimed at organisations that want to use AI agents in software development without setting up separate AI infrastructure.

Native integration

Under the expanded partnership, GitLab Duo Agent Platform now integrates natively with Vertex AI. Customers can use models they already run on Google Cloud from within GitLab, rather than switching between separate systems.

GitLab acts as a system of record for issues, code, merge requests, pipelines and security findings. In practice, this means an AI agent generating a code suggestion can draw on the issue behind the task, the existing repository and the continuous integration pipeline that tests the result.

Every agent action passes through the same access controls, approval rules and audit logging used by developers. GitLab presents that governance layer as a way to maintain oversight as AI systems take on more tasks across the software lifecycle.

Cloud spend

A central part of the partnership is commercial rather than technical. Customers with existing Google Cloud commitments can count GitLab Duo Agent Platform usage towards that spend, which may make adoption easier for enterprises already operating under broader cloud purchasing agreements.

The companies also said organisations can run GitLab's AI Gateway on Google Cloud without provisioning or managing separate AI infrastructure. For teams already on Google Cloud, that keeps AI workloads on infrastructure they already use.

GitLab's AI Gateway can run on Google Cloud services such as GKE or Cloud Run, whether the gateway is managed by GitLab or self-hosted by the customer. For self-hosted users, GitLab also offers a Bring Your Own Model option that lets teams connect approved models and gateways.

Model choice

Through Vertex AI Model Garden, customers can access a range of foundation models, including Gemini. GitLab said this gives teams flexibility to choose models based on factors such as cost, performance or regulatory requirements.

The emphasis on model choice reflects a broader market trend, as software companies seek to avoid locking customers into a single large language model provider. By integrating with Vertex AI, GitLab can offer access to Google's own models alongside a wider set of options available through Google Cloud's platform.

For GitLab, the partnership also strengthens its argument that AI in software development should sit within the tools where work is already tracked and approved. Rather than offering agents as separate assistants, it is tying them to the records, controls and workflows already used by development, security and operations teams.

"Google Cloud provides cutting-edge technology that helps partners innovate and deliver more impactful solutions for business transformation," said Ritika Suri, Managing Director, AI and Data Partnerships at Google Cloud. "Through our partnership with GitLab, we will provide customers with innovative capabilities that can improve operations, enhance customer experiences, and drive innovation in the DevSecOps industry," added Suri.

GitLab also framed the partnership around the quality of context available to AI systems operating inside software teams. Access to issues, code history, pipelines and security findings is important if agents are to carry out useful work under established controls, it said.

"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, 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," added Khurana.