DigestAI news desk

Cut through the AI noise.

Enterprise & Industry2 min read

GitLab adds Microsoft Foundry support to Duo self-hosted AI

GitLab announced an expansion of its Duo Self-Hosted offering to work with models deployed through Microsoft Foundry. The integration supports model families from OpenAI GPT, Anthropic Claude, Meta Llama and Mistral, allowing enterprises to run AI development capabilities inside their own Azure environment.

1 source

Key points

  • GitLab Duo Self-Hosted now connects to Microsoft Foundry models, including OpenAI GPT, Anthropic Claude, Meta Llama, and Mistral.
  • Enterprises can run AI workflows in their own Azure environment, keeping data residency and control over model deployment.
  • Teams must manage model capacity, networking, credentials and compatibility, as GitLab no longer hosts the models.

The architecture consists of a self‑managed GitLab instance, a self‑hosted GitLab AI Gateway, and one or more model endpoints hosted on Foundry. Feature‑level model selection lets teams assign different models to code suggestions, agentic workloads or high‑volume tasks, and swap models without altering the development workflow. The move targets organizations with data residency, sovereignty, regulatory or network isolation requirements.

GitLab notes that this flexibility shifts operational responsibility to engineering and platform teams, who must handle model deployment, capacity, networking, credentials, availability and lifecycle. Compatibility between Microsoft Foundry’s catalog and GitLab’s supported matrix must be verified, highlighting a broader shift toward model‑agnostic control layers where the DevSecOps platform manages workflow while the organization controls the underlying AI models.

Full story from infoq.com · by Craig Risi · via Search: MicrosoftOpen source ↗

GitLab Duo Expands Self-Hosted AI Options Through Microsoft Foundry

infoq.com · 22 September 2026

Loading the full article…

This text was published by infoq.com and written by Craig Risi. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories