GitLab 18.3 advances AI orchestration & agent integration in coding

GitLab has released version 18.3 of its platform with expanded features aimed at supporting AI orchestration in software engineering workflows.

This release seeks to address integration issues faced by organisations looking to make artificial intelligence tools work collaboratively alongside human development teams. According to GitLab, the latest update broadens the platform's orchestration capability, strengthens governance at an enterprise scale, and supports deeper integrations for both human and AI participants in the software development process.

AI collaboration

The update builds on GitLab's DevSecOps foundation by embedding AI across three areas: the system of record, the software control plane, and the integrated user experience. These updates are designed to make it easier for engineering teams to use AI within familiar workflows rather than treating AI agents as siloed elements.

The system of record function allows GitLab to serve as a secure and contextual base for digital assets, including source code and project plans, that enable AI use in a protected environment. In the software control plane, the orchestration of business processes now includes a layer for multi-agent flows. The integrated user experience aims to remove the need for context-switching by providing a unified interface for the full software development lifecycle.

MCP server and universal AI integration

Among the features in GitLab 18.3 is the MCP (Model Context Protocol) server, which allows third-party AI systems to integrate with GitLab projects and processes over a standardised interface. The intention is to remove the need for labour-intensive custom integrations and enable AI tools - such as Cursor - to interact with GitLab projects securely and contextually.

"Bringing GitLab workflows directly into Cursor is a critical step in reducing friction for developers. By minimising the need for context switching, teams can check issue status, review merge requests, and monitor pipeline results without ever leaving their coding environment. This integration is a natural fit for our shared customers, and we look forward to a long-term partnership with GitLab to continue enhancing developer productivity." - Ricky Doar, VP of Field Engineering at Cursor

Agent support for major AI models

CLI agent support is also introduced for major AI models including Claude Code, Codex, Amazon Q, Google Gemini, and opencode through a bring-your-own-key method. The new integration allows engineering teams to delegate routine tasks to AI agents using mentions in issues or merge requests, which can help reduce the repetitive workload for developers.

"GitLab's MCP server and CLI agent support create powerful new ways for Amazon Q to integrate with development workflows. Amazon Q Developer can now connect directly through GitLab's remote MCP interface, while teams can delegate development tasks by simply @ mentioning Amazon Q CLI in issues and merge requests. The robust security and governance capabilities built into these integrations give enterprises the confidence to leverage AI coding tools while preserving their development standards. Our partnership with GitLab demonstrates AWS' ongoing commitment to expanding our AI ecosystem and making intelligent development tools accessible wherever developers work." - Deepak Singh, Vice President of Developer Agents and Experiences at AWS

"Bringing Claude Code directly into GitLab puts AI assistance where millions of developers already collaborate and ship code daily. The ability to mention Claude directly in issues and merge requests removes friction while maintaining quality with human oversight and review processes. This update brings Claude Code's capabilities to more places where teams work, making AI a natural part of their developer workflow." - Cat Wu, Claude Code Product Lead, Anthropic

"With GitLab's new agent integration in 18.3 you can use opencode within your existing workflows. You can @mention opencode in an issue or merge request and it'll run your agent right in your CI pipeline. This ability to configure and run opencode the way you want is the type of integration we know the open source community really values."- Jay V., CEO, opencode

Workflow transparency and intelligence

The update also introduces Agent Insights, which aims to provide transparency about the decision-making processes of AI agents. This visibility allows organisations to optimise their workflows and helps teams follow best practices with a record of agent activities.

Additionally, the Knowledge Graph functionality now offers real-time code indexing. This enhancement is expected to accelerate code searches and improve contextual accuracy in search results, allowing teams to access actionable insights into their codebase more efficiently.

Further development of AI flows

Building on features from the previous release, the AI Flows update now includes new workflows such as the issue to merge request flow, which is intended to speed up the movement from idea to code. Another new capability is the convert CI File Flow, designed to enable seamless migration intelligence between projects or code pipelines.

These developments reflect GitLab's approach to human and AI collaboration, focusing on increased productivity and maintenance of established development practices. The 18.3 release signals a continued effort to integrate AI deeply into software engineering while retaining necessary safeguards and workflow familiarity for teams.