More AI models for GitLab Duo Agent Platform Self-Hosted

2026-05-21 · Source: GitLab · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Intermediate, quick

Summary

GitLab 19.0, released on May 21, 2026, significantly enhances the Duo Agent Platform Self-Hosted by introducing broader support for open source AI models. This update directly addresses the needs of customers operating in highly secure air-gapped and regulated environments, providing them with more capable artificial intelligence options. The expansion of model compatibility allows these organizations to integrate advanced AI functionalities while maintaining strict control over their data and infrastructure, ensuring compliance and operational security. This development aims to empower self-hosted users with greater flexibility and performance for their AI-driven workflows within their existing secure setups.

Key takeaway

For AI Architects or MLOps Engineers deploying solutions in air-gapped or highly regulated environments, GitLab 19.0's expanded open source model support for Duo Agent Platform Self-Hosted is a critical update. You can now integrate more capable AI functionalities directly within your secure infrastructure, reducing reliance on external services and simplifying compliance. Evaluate these new options to enhance your self-hosted AI capabilities while maintaining stringent data governance and operational security.

Key insights

GitLab 19.0 expands open source AI model support for self-hosted platforms in secure, regulated environments.

Principles

• Prioritize secure AI deployment.
• Offer flexible open source options.
• Support air-gapped operations.

In practice

• Deploy AI in air-gapped networks.
• Utilize open source models securely.
• Meet regulatory compliance.

Topics

• GitLab 19.0
• Duo Agent Platform
• Self-Hosted AI
• Open-Source Models
• Air-gapped Environments
• Regulated Environments

Best for: CTO, VP of Engineering/Data, Director of AI/ML, MLOps Engineer, AI Architect, AI Engineer

Related on AIssential

• GitLab, Google Cloud expand integration with Vertex AI for DevSecOps — Expanded Google Cloud and GitLab partnership integrates Vertex AI models into DevSecOps workflows with robust governance.
• Codex and GitLab: From code fix to production — Integrating AI tools like Codex with platforms like GitLab streamlines the entire code fix to production workflow.
• GitLab 19.0 released — The release deepens AI integration and security automation while streamlining CI/CD and platform management.
• openclaw / openclaw — OpenClaw provides a self-hosted, multi-channel AI assistant with robust integration and security features.
• 🤖AI Agents Weekly: GPT-5.3-Codex-Spark, GLM-5, MiniMax M2.5, Recursive Language Models, Harness Engineering, Agentica, and More — New agentic coding and reasoning models demonstrate self-development capabilities and significant performance gains.
• Noticed a big spike on OpenRouter’s Cloud Agents (Coding) leaderboard this week — The gitlawb platform's 582 billion token usage on OpenRouter signals significant AI agent activity in decentralized code collaboration.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by GitLab.