GitLab extends AWS partnership

DevSecOps orchestration platform GitLab has announced that joint customers of the company and Amazon Web Services (AWS) can now route GitLab Duo Agent Platform inference through Amazon Bedrock.

For organisations that have already standardised on AWS, this integration brings GitLab Duo Agent Platform into their existing environment, from approved models in Amazon Bedrock, to access controls in IAM, and usage that counts toward existing AWS spend.

This means there's no new vendor risk assessment, no separate model endpoint to provision, and no additional billing relationship to manage, according to GitLab.

GitLab's orchestration layer adds workflow-level governance on top of what Amazon Bedrock already enforces at the model level.

This integration builds on GitLab's recent Bring Your Own Model capability for self-managed customers. With BYOM, teams route inference from a self-hosted AI Gateway directly to Amazon Bedrock in their own AWS environment, so source code and inference traffic never leave the customer's network boundary.

Teams that have fine-tuned models on Amazon Bedrock can use those directly. Teams that prefer GitLab-managed models, now including the latest Anthropic Claude models available on Amazon Bedrock, can use those instead. GitLab handles the orchestration and governance regardless of which path a team chooses.

GitLab is already the system of record for merge requests, pipelines, and security findings, which means admin-defined policies control which models agents can call, audit logs capture every agent action alongside the code it produced and teams can establish approved configurations so agents operate consistently across projects and regions.

“GitLab Duo Agent Platform on Amazon Bedrock means customers can deploy agentic AI for software development without standing up new infrastructure, negotiating new contracts, or rethinking their security posture,” said Rahul Pathak, vice president, data & AI GTM at AWS.

“It runs inside their existing AWS environment — same IAM policies, same compliance controls, same spending commitments. That’s how AI adoption should work.” 

“Most enterprise leaders I talk to want to adopt agentic AI without building a second stack next to the cloud environment they already use,” said Manav Khurana, chief product and marketing officer at GitLab.

“For AWS customers, this integration makes that possible. GitLab Duo Agent Platform runs through Amazon Bedrock accounts they already manage, governed by policies they already enforce, and funded by commitments they've already made. AI adoption scales when it fits into decisions already made, not when it asks teams to make new ones."