[{"data":1,"prerenderedAt":826},["ShallowReactive",2],{"/en-us/blog/gitlab-18-5-intelligence-that-moves-software-development-forward":3,"navigation-en-us":38,"banner-en-us":459,"footer-en-us":469,"blog-post-authors-en-us-Bill Staples":710,"blog-related-posts-en-us-gitlab-18-5-intelligence-that-moves-software-development-forward":725,"blog-promotions-en-us":764,"next-steps-en-us":816},{"id":4,"title":5,"authorSlugs":6,"authors":8,"body":10,"category":11,"categorySlug":11,"config":12,"content":16,"date":24,"description":17,"extension":25,"externalUrl":26,"featured":15,"heroImage":19,"isFeatured":15,"meta":27,"navigation":15,"path":28,"publishedDate":24,"rawbody":29,"seo":30,"slug":14,"stem":33,"tagSlugs":34,"tags":36,"template":13,"updatedDate":26,"__hash__":37},"blogPosts/en-us/blog/gitlab-18-5-intelligence-that-moves-software-development-forward.md","GitLab 18.5: Intelligence that moves software development forward",[7],"bill-staples",[9],"Bill Staples","Software development teams are drowning in noise. Thousands of vulnerabilities flood security dashboards, but only a fraction pose real risk. Developers context-switch between planning backlogs, triaging security findings, reviewing code, and responding to CI/CD failures — losing hours to manual work. [GitLab 18.5](https://docs.gitlab.com/releases/18/gitlab-18-5-released/) calms this chaos.\n\nAt the heart of this release is a valuable improvement in overall usability of GitLab and how AI integrates into your user experience. A new panel-based UI makes it easier to see data in context, and allows GitLab Duo Chat to be persistently visible across the platform, wherever it is needed. Purpose-built agents tackle vulnerability triage and backlog management, and popular AI tools integrate with agentic workflows even more seamlessly than before. We’ve also extended our market-leading security capabilities to help you better identify exploitable vulnerabilities versus theoretical ones, distinguish active credentials from expired ones, and scan only changed code to keep developers in flow.\n\n## What’s new in 18.5\n\n18.5 represents our biggest release so far this year — watch our introduction to the release, and read more details below.\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128975773?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"GitLab_18.5 Release_101925_MP_v2\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\n### Modern user experience with quick access to GitLab Duo everywhere\n\nGitLab 18.5 delivers a modernized user experience with a more intuitive interface driven by a new panel-based layout.\n\nWith panels, key information appears side by side so that you can work contextually, without losing your place. For example, when you click on an issue in the issues list, its details automatically open in a side panel. You can also launch the GitLab Duo panel on the right, bringing Duo wherever you are in GitLab. This lets you ask contextual questions or give instructions, right alongside your work.\n\nSeveral usability improvements make navigation easier. The global search box now appears at the top center for improved accessibility. Global navigation elements, including Issues, Merge Requests, To-Dos, and your avatar have moved to the top right. Additionally, the left sidebar is now collapsible and expandable, giving you more control over your workspace.\n\nTeams using experimental and GitLab Duo beta features will be the first to receive the new interface, followed by all GitLab.com users who will be able to turn this experience on using the toggle located under your user icon. To learn more about this feature, reference our documentation [here](https://docs.gitlab.com/user/interface_redesign/#turn-new-navigation-on-or-off). Please share your feedback or report any issues [here](https://gitlab.com/gitlab-org/gitlab/-/issues/577554), you're helping us shape a better GitLab!\n\n### Updates to GitLab Duo Agent Platform\n\n**Security Analyst Agent: Transform manual vulnerability triage into intelligent automation**\n\nGitLab Duo [Security Analyst Agent](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/security_analyst_agent/) automates vulnerability management workflows through AI-powered analysis, helping transform hours of manual triage into intelligent automation. Building on the Vulnerability Management Tools available through GitLab Duo Agentic Chat, Security Analyst Agent orchestrates multiple tools, applying security policies, and creating custom flows for recurring workflows automatically.\n\nSecurity teams can access enriched vulnerability data, including CVE details, static reachability analysis, and code flow information, while executing operations like dismissing false positives, confirming threats, adjusting severity levels, and creating linked issues for remediation — all through conversational AI. The agent reduces repetitive clicking through vulnerability dashboards and replaces custom scripts with simple natural language commands.\n\nFor example, when a security scan reveals dozens of vulnerabilities, simply prompt: \"Dismiss vulnerabilities with reachable=FALSE and create issues for critical findings.\" Security Analyst Agent analyzes reachability data, applies security policies, and completes bulk operations in moments — helping decrease work that would otherwise take hours.\n\nWhile individual Vulnerability Management Tools can be accessed directly through Agentic Chat for specific tasks, Security Analyst Agent orchestrates these tools intelligently and automates complex multi-step workflows. Note that Vulnerability Management Tools are available through Agentic Chat on GitLab Self-managed and GitLab.com instances, and Security Analyst Agent is available on GitLab.com only for 18.5, while availability in Self-managed and Dedicated environments will come with our next release.\nWatch this demo:\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128975984?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.5 Security Demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\n**GitLab Duo Planner: Turn backlog chaos into strategic clarity**\n\nManaging complex software delivery requires constant context-switching between planning tasks. [GitLab Duo Planner](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/planner/) addresses the real-world planning challenges we see teams face every day. Duo Planner acts as your teammate with awareness of your project context, including how you manage issues, epics, and merge requests. Unlike generic AI assistants, it's purpose-built with deep knowledge of GitLab's planning workflows coupled with Agile and prioritization frameworks to help you balance effort, risk, and strategic alignment.\n\nGitLab Duo Planner can turn vague ideas into structured planning hierarchies, identify stale backlog items, and draft executive updates. For example, when refining your backlog with hundreds of issues accumulated over months, simply prompt: \"Identify stale backlog items and suggest priorities.\" Within seconds, you'll receive a structured summary showing issues without recent activity, items missing key details, duplicate work, and recommended priorities based on labels and milestones, complete with actionable recommendations.\n\nFor teams managing complex roadmaps, the Planner aims to eliminate hours of manual analysis and context-switching, helping Product Managers and engineering leads make faster, more informed decisions. As of 18.5, GitLab Duo Planner is currently “read-only,” meaning that it can analyze, plan, and suggest, but cannot yet take direct action to modify anything. Please see our [documentation](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/planner/) for more information.\n\n**Extensible Agent Catalog: Popular AI tools as native GitLab agents**\n\nGitLab 18.5 introduces popular AI agents directly into the [AI Catalog](https://docs.gitlab.com/user/duo_agent_platform/ai_catalog/), making external tools like Claude, OpenAI Codex, Google Gemini CLI, Amazon Q Developer, and OpenCode available as native GitLab agents. Users can now discover, configure, and deploy these agents through the same unified catalog interface used for GitLab's built-in agents, with automatic syncing of foundational agents across organization catalogs.\n\nThis eliminates the complexity of manual agent setup by providing a point-and-click catalog experience while maintaining enterprise-grade security through GitLab's authentication and audit systems. GitLab Duo Enterprise subscriptions now include built-in usage of Claude and Codex within GitLab, allowing you to use your existing GitLab subscription for these tools without requiring separate API keys or additional billing setup. Other agents may still require separate subscriptions and configuration while we finalize our integration plans.\n\n**Self-hosted GitLab Duo Agent Platform (Beta): Address data sovereignty requirements without sacrificing AI power**\n\nGitLab 18.5 moves GitLab Duo Agent Platform's self-hosted capabilities from experimental to beta, enabling organizations to execute AI agents and flows entirely within their own infrastructure — critical for regulated industries and data sovereignty requirements. The beta release includes improved timeout configurations and AI Gateway settings, allowing teams to use AI agents for code reviews, bug fixes, and feature implementations, while providing enterprise-grade security for sensitive code.\n\n## Smarter, faster security: Prioritize real risks and keep developers in the flow\n\nGitLab 18.5 introduces new application security capabilities that help teams focus on exploitable risk, reduce noise, and strengthen software supply chain security. These updates continue our commitment to building security directly into the development process — delivering precision, speed, and insight without disrupting developer flow.\n\n**Static Reachability Analysis**\n\nWith over [37,000 new CVEs](https://www.cvedetails.com/) issued this year, security teams face an overwhelming volume of vulnerabilities and struggle to understand which ones are truly exploitable. Static Reachability Analysis, now in limited availability, brings library-level precision by helping to identify whether vulnerable code is actually invoked in your application, not just present in dependencies.\n\nPaired with our [recently released](https://docs.gitlab.com/user/application_security/vulnerabilities/risk_assessment_data/) Exploit Prediction Scoring System (EPSS) and Known Exploited Vulnerability (KEV) data, security teams can more effectively accelerate vulnerability triage and prioritize real risks to help strengthen overall supply chain security. In 18.5, we’re adding support for Java, alongside existing support for Python, JavaScript, and TypeScript.\n\n**Secret Validity Checks**\n\nJust as Static Reachability Analysis helps teams prioritize exploitable vulnerabilities from open source dependencies, Secret Validity Checks bring the same insight to exposed secrets — currently available in beta on GitLab.com and GitLab Self-Managed. For GitLab-issued security tokens, instead of manually verifying whether a leaked credential or API key is active, GitLab automatically distinguishes active secrets from expired ones directly in the [Vulnerability Report](https://docs.gitlab.com/user/application_security/vulnerability_report/). This helps enable security and development teams to focus remediation efforts on genuine risks. Support for AWS- and GCP-issued secrets is planned for future releases.\n\n**Custom rules for Advanced SAST**\n\nAdvanced SAST runs on rules informed by our in-house security research team, designed to maximize accuracy out of the box. However, some teams required additional flexibility to tune the SAST engine for their specific organization. With Custom Rules for Advanced SAST, AppSec teams can define atomic, pattern-based detection logic to help capture security issues specific to their organization — like flagging banned function calls — while still using GitLab’s curated ruleset as the baseline. Customizations are managed through simple TOML files, just like other SAST ruleset configurations. While these rules will not support taint analysis, they do give organizations greater flexibility in achieving accurate SAST results.\n\n**Advanced SAST C and C++ language support**\n\nWe’re expanding our language coverage for Advanced SAST to include C and C++, which are widely used languages in embedded systems software development. To enable scanning, projects must generate a compilation database that captures compiler commands and includes paths used during builds. This works to ensure the scanner can accurately parse and analyze source files, delivering precise, context-aware results that help security teams identify real vulnerabilities in the development process. The implementation requirements for C and C++ require specific configurations, which can be found in our [documentation](https://docs.gitlab.com/user/application_security/sast/cpp_advanced_sast/). Advanced SAST C and C++ support are currently available in beta.\n\n**Diff-based SAST scanning**\n\nTraditional SAST scans re-analyze entire codebases with every commit, slowing pipelines and disrupting developer flow. The developer experience is a critical consideration that can make or break the adoption of application security testing. Diff-based SAST scanning aims to speed up scan times by focusing only on the code changed in a merge request, reducing redundant analysis and surfacing relevant results tied to the developer’s work. By aligning scans with actual code changes, GitLab delivers faster, more focused feedback that helps keep developers in flow while maintaining strong security coverage.\n\n## Simplify API configurations\n\nAPI-driven workflows offer power and flexibility, but they can also create unnecessary complexity for tasks that teams need to perform regularly. The new Maven Virtual Registry interface brings a UI layer to these operations.\n\n### Maven Virtual Registry interface\n\nThe new web-based interface for managing Maven Virtual Registries turns complex API configurations into visual simplicity, providing a more intuitive experience for package administrators and platform engineers.\n\nPreviously, teams configured and maintained virtual registries only through API calls, which made routine maintenance time-consuming and required specialized platform knowledge. The new interface removes that barrier, helping to make everyday tasks faster and easier.\n\nWith this update, you can now:\n\n* Create virtual registries to simplify dependency configuration\n* Create and order upstreams to help improve performance and compliance\n* Browse and clear stale cache entries directly in the UI\n\nThis visual experience helps reduce operational overhead and provides development teams with clearer insight into how dependencies are resolved, enabling them to make better decisions about build performance and security policies.\n\nWatch a demo:\n\n\u003C!-- blank line -->\n\u003Cfigure class=\"video_container\">\n\u003Ciframe src=\"https://www.youtube.com/embed/CiOZJPhAvaI?si=cYaoR_OIgqFKbyM2\" frameborder=\"0\" allowfullscreen=\"true\"> \u003C/iframe>\n\u003C/figure>\n\u003C!-- blank line -->\n\n\u003Cp>\u003C/p>\n\nWe invite enterprise customers to join the [Maven Virtual Registry Beta program](https://gitlab.com/gitlab-org/gitlab/-/issues/543045) and share feedback to help shape the final release.\n\n## AI that adapts to your workflow\n\nThis release represents more than new capabilities — it's about choice and control. Watch the walkthrough video here:\n\n\u003Cp>\u003C/p>\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128992281?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.5-tech-demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\nGitLab Premium and Ultimate users can start using these capabilities today on [GitLab.com](https://GitLab.com) and self-managed environments, with availability for GitLab Dedicated customers planned for next month.\n\nGitLab Duo Agent Platform is currently in **beta** — enable beta and experimental features to experience how full-context AI can transform the way your teams build software. New to GitLab? [Start your free trial](https://about.gitlab.com/free-trial/devsecops/) and see why the future of development is AI-powered, secure, and orchestrated through the world’s most comprehensive DevSecOps platform.\n\n***Note:** Platform capabilities that are in beta are available as part of the GitLab Beta program. They are free to use during the beta period, and when generally available, they will be made available with a paid add-on option for GitLab Duo Agent Platform.*\n\n### Stay up to date with GitLab\n\nTo make sure you’re getting the latest features, security updates, and performance improvements, we recommend keeping your GitLab instance up to date. The following resources can help you plan and complete your upgrade:\n\n* [Upgrade Path Tool](https://gitlab-com.gitlab.io/support/toolbox/upgrade-path/) – enter your current version and see the exact upgrade steps for your instance\n* [Upgrade Documentation](https://docs.gitlab.com/update/upgrade_paths/) – detailed guides for each supported version, including requirements, step-by-step instructions, and best practices\n\nBy upgrading regularly, you’ll ensure your team benefits from the newest GitLab capabilities and remains secure and supported.\n\nFor organizations that want a hands-off approach, consider [GitLab’s Managed Maintenance service](https://content.gitlab.com/viewer/d1fe944dddb06394e6187f0028f010ad#1). With Managed Maintenance, your team stays focused on innovation while GitLab experts keep your Self-Managed instance reliably upgraded, secure, and ready to lead in DevSecOps. Ask your account manager for more information.\n\n*This blog post contains \"forward‑looking statements\" within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934. Although we believe that the expectations reflected in these statements are reasonable, they are subject to known and unknown risks, uncertainties, assumptions and other factors that may cause actual results or outcomes to differ materially. Further information on these risks and other factors is included under the caption \"Risk Factors\" in our filings with the SEC. We do not undertake any obligation to update or revise these statements after the date of this blog post, except as required by law.*","ai-ml",{"template":13,"slug":14,"featured":15},"BlogPost","gitlab-18-5-intelligence-that-moves-software-development-forward",true,{"title":5,"description":17,"authors":18,"heroImage":19,"tags":20,"category":11,"date":24,"body":10},"GitLab 18.5 delivers new specialized agents, security insights that cut through the noise, and a reimagined interface that keeps your AI teammate always in view.",[9],"https://res.cloudinary.com/about-gitlab-com/image/upload/v1760970883/asrc2c2hejqp5o1tan4c.png",[21,22,23],"features","product","DevSecOps platform","2025-10-21","md",null,{},"/en-us/blog/gitlab-18-5-intelligence-that-moves-software-development-forward","---\nseo:\n  config:\n    noIndex: false\n  title: 'GitLab 18.5: Intelligence that moves software development forward'\n  description: GitLab 18.5 delivers new specialized agents,\n    security insights that cut through the noise, and a reimagined interface\n    that keeps your AI teammate always in view.\ntitle: 'GitLab 18.5: Intelligence that moves software development forward'\ndescription: GitLab 18.5 delivers new specialized agents, security insights that cut through the noise, and a reimagined interface that keeps your AI teammate always in view.\nauthors:\n  - Bill Staples\nheroImage: https://res.cloudinary.com/about-gitlab-com/image/upload/v1760970883/asrc2c2hejqp5o1tan4c.png\ntags:\n  - features\n  - product\n  - DevSecOps platform\ncategory: ai-ml\ndate: '2025-10-21'\nslug: gitlab-18-5-intelligence-that-moves-software-development-forward\nfeatured: true\ntemplate: BlogPost\n---\n\nSoftware development teams are drowning in noise. Thousands of vulnerabilities flood security dashboards, but only a fraction pose real risk. Developers context-switch between planning backlogs, triaging security findings, reviewing code, and responding to CI/CD failures — losing hours to manual work. [GitLab 18.5](https://docs.gitlab.com/releases/18/gitlab-18-5-released/) calms this chaos.\n\nAt the heart of this release is a valuable improvement in overall usability of GitLab and how AI integrates into your user experience. A new panel-based UI makes it easier to see data in context, and allows GitLab Duo Chat to be persistently visible across the platform, wherever it is needed. Purpose-built agents tackle vulnerability triage and backlog management, and popular AI tools integrate with agentic workflows even more seamlessly than before. We’ve also extended our market-leading security capabilities to help you better identify exploitable vulnerabilities versus theoretical ones, distinguish active credentials from expired ones, and scan only changed code to keep developers in flow.\n\n## What’s new in 18.5\n\n18.5 represents our biggest release so far this year — watch our introduction to the release, and read more details below.\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128975773?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"GitLab_18.5 Release_101925_MP_v2\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\n### Modern user experience with quick access to GitLab Duo everywhere\n\nGitLab 18.5 delivers a modernized user experience with a more intuitive interface driven by a new panel-based layout.\n\nWith panels, key information appears side by side so that you can work contextually, without losing your place. For example, when you click on an issue in the issues list, its details automatically open in a side panel. You can also launch the GitLab Duo panel on the right, bringing Duo wherever you are in GitLab. This lets you ask contextual questions or give instructions, right alongside your work.\n\nSeveral usability improvements make navigation easier. The global search box now appears at the top center for improved accessibility. Global navigation elements, including Issues, Merge Requests, To-Dos, and your avatar have moved to the top right. Additionally, the left sidebar is now collapsible and expandable, giving you more control over your workspace.\n\nTeams using experimental and GitLab Duo beta features will be the first to receive the new interface, followed by all GitLab.com users who will be able to turn this experience on using the toggle located under your user icon. To learn more about this feature, reference our documentation [here](https://docs.gitlab.com/user/interface_redesign/#turn-new-navigation-on-or-off). Please share your feedback or report any issues [here](https://gitlab.com/gitlab-org/gitlab/-/issues/577554), you're helping us shape a better GitLab!\n\n### Updates to GitLab Duo Agent Platform\n\n**Security Analyst Agent: Transform manual vulnerability triage into intelligent automation**\n\nGitLab Duo [Security Analyst Agent](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/security_analyst_agent/) automates vulnerability management workflows through AI-powered analysis, helping transform hours of manual triage into intelligent automation. Building on the Vulnerability Management Tools available through GitLab Duo Agentic Chat, Security Analyst Agent orchestrates multiple tools, applying security policies, and creating custom flows for recurring workflows automatically.\n\nSecurity teams can access enriched vulnerability data, including CVE details, static reachability analysis, and code flow information, while executing operations like dismissing false positives, confirming threats, adjusting severity levels, and creating linked issues for remediation — all through conversational AI. The agent reduces repetitive clicking through vulnerability dashboards and replaces custom scripts with simple natural language commands.\n\nFor example, when a security scan reveals dozens of vulnerabilities, simply prompt: \"Dismiss vulnerabilities with reachable=FALSE and create issues for critical findings.\" Security Analyst Agent analyzes reachability data, applies security policies, and completes bulk operations in moments — helping decrease work that would otherwise take hours.\n\nWhile individual Vulnerability Management Tools can be accessed directly through Agentic Chat for specific tasks, Security Analyst Agent orchestrates these tools intelligently and automates complex multi-step workflows. Note that Vulnerability Management Tools are available through Agentic Chat on GitLab Self-managed and GitLab.com instances, and Security Analyst Agent is available on GitLab.com only for 18.5, while availability in Self-managed and Dedicated environments will come with our next release.\nWatch this demo:\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128975984?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.5 Security Demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\n**GitLab Duo Planner: Turn backlog chaos into strategic clarity**\n\nManaging complex software delivery requires constant context-switching between planning tasks. [GitLab Duo Planner](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/planner/) addresses the real-world planning challenges we see teams face every day. Duo Planner acts as your teammate with awareness of your project context, including how you manage issues, epics, and merge requests. Unlike generic AI assistants, it's purpose-built with deep knowledge of GitLab's planning workflows coupled with Agile and prioritization frameworks to help you balance effort, risk, and strategic alignment.\n\nGitLab Duo Planner can turn vague ideas into structured planning hierarchies, identify stale backlog items, and draft executive updates. For example, when refining your backlog with hundreds of issues accumulated over months, simply prompt: \"Identify stale backlog items and suggest priorities.\" Within seconds, you'll receive a structured summary showing issues without recent activity, items missing key details, duplicate work, and recommended priorities based on labels and milestones, complete with actionable recommendations.\n\nFor teams managing complex roadmaps, the Planner aims to eliminate hours of manual analysis and context-switching, helping Product Managers and engineering leads make faster, more informed decisions. As of 18.5, GitLab Duo Planner is currently “read-only,” meaning that it can analyze, plan, and suggest, but cannot yet take direct action to modify anything. Please see our [documentation](https://docs.gitlab.com/user/duo_agent_platform/agents/foundational_agents/planner/) for more information.\n\n**Extensible Agent Catalog: Popular AI tools as native GitLab agents**\n\nGitLab 18.5 introduces popular AI agents directly into the [AI Catalog](https://docs.gitlab.com/user/duo_agent_platform/ai_catalog/), making external tools like Claude, OpenAI Codex, Google Gemini CLI, Amazon Q Developer, and OpenCode available as native GitLab agents. Users can now discover, configure, and deploy these agents through the same unified catalog interface used for GitLab's built-in agents, with automatic syncing of foundational agents across organization catalogs.\n\nThis eliminates the complexity of manual agent setup by providing a point-and-click catalog experience while maintaining enterprise-grade security through GitLab's authentication and audit systems. GitLab Duo Enterprise subscriptions now include built-in usage of Claude and Codex within GitLab, allowing you to use your existing GitLab subscription for these tools without requiring separate API keys or additional billing setup. Other agents may still require separate subscriptions and configuration while we finalize our integration plans.\n\n**Self-hosted GitLab Duo Agent Platform (Beta): Address data sovereignty requirements without sacrificing AI power**\n\nGitLab 18.5 moves GitLab Duo Agent Platform's self-hosted capabilities from experimental to beta, enabling organizations to execute AI agents and flows entirely within their own infrastructure — critical for regulated industries and data sovereignty requirements. The beta release includes improved timeout configurations and AI Gateway settings, allowing teams to use AI agents for code reviews, bug fixes, and feature implementations, while providing enterprise-grade security for sensitive code.\n\n## Smarter, faster security: Prioritize real risks and keep developers in the flow\n\nGitLab 18.5 introduces new application security capabilities that help teams focus on exploitable risk, reduce noise, and strengthen software supply chain security. These updates continue our commitment to building security directly into the development process — delivering precision, speed, and insight without disrupting developer flow.\n\n**Static Reachability Analysis**\n\nWith over [37,000 new CVEs](https://www.cvedetails.com/) issued this year, security teams face an overwhelming volume of vulnerabilities and struggle to understand which ones are truly exploitable. Static Reachability Analysis, now in limited availability, brings library-level precision by helping to identify whether vulnerable code is actually invoked in your application, not just present in dependencies.\n\nPaired with our [recently released](https://docs.gitlab.com/user/application_security/vulnerabilities/risk_assessment_data/) Exploit Prediction Scoring System (EPSS) and Known Exploited Vulnerability (KEV) data, security teams can more effectively accelerate vulnerability triage and prioritize real risks to help strengthen overall supply chain security. In 18.5, we’re adding support for Java, alongside existing support for Python, JavaScript, and TypeScript.\n\n**Secret Validity Checks**\n\nJust as Static Reachability Analysis helps teams prioritize exploitable vulnerabilities from open source dependencies, Secret Validity Checks bring the same insight to exposed secrets — currently available in beta on GitLab.com and GitLab Self-Managed. For GitLab-issued security tokens, instead of manually verifying whether a leaked credential or API key is active, GitLab automatically distinguishes active secrets from expired ones directly in the [Vulnerability Report](https://docs.gitlab.com/user/application_security/vulnerability_report/). This helps enable security and development teams to focus remediation efforts on genuine risks. Support for AWS- and GCP-issued secrets is planned for future releases.\n\n**Custom rules for Advanced SAST**\n\nAdvanced SAST runs on rules informed by our in-house security research team, designed to maximize accuracy out of the box. However, some teams required additional flexibility to tune the SAST engine for their specific organization. With Custom Rules for Advanced SAST, AppSec teams can define atomic, pattern-based detection logic to help capture security issues specific to their organization — like flagging banned function calls — while still using GitLab’s curated ruleset as the baseline. Customizations are managed through simple TOML files, just like other SAST ruleset configurations. While these rules will not support taint analysis, they do give organizations greater flexibility in achieving accurate SAST results.\n\n**Advanced SAST C and C++ language support**\n\nWe’re expanding our language coverage for Advanced SAST to include C and C++, which are widely used languages in embedded systems software development. To enable scanning, projects must generate a compilation database that captures compiler commands and includes paths used during builds. This works to ensure the scanner can accurately parse and analyze source files, delivering precise, context-aware results that help security teams identify real vulnerabilities in the development process. The implementation requirements for C and C++ require specific configurations, which can be found in our [documentation](https://docs.gitlab.com/user/application_security/sast/cpp_advanced_sast/). Advanced SAST C and C++ support are currently available in beta.\n\n**Diff-based SAST scanning**\n\nTraditional SAST scans re-analyze entire codebases with every commit, slowing pipelines and disrupting developer flow. The developer experience is a critical consideration that can make or break the adoption of application security testing. Diff-based SAST scanning aims to speed up scan times by focusing only on the code changed in a merge request, reducing redundant analysis and surfacing relevant results tied to the developer’s work. By aligning scans with actual code changes, GitLab delivers faster, more focused feedback that helps keep developers in flow while maintaining strong security coverage.\n\n## Simplify API configurations\n\nAPI-driven workflows offer power and flexibility, but they can also create unnecessary complexity for tasks that teams need to perform regularly. The new Maven Virtual Registry interface brings a UI layer to these operations.\n\n### Maven Virtual Registry interface\n\nThe new web-based interface for managing Maven Virtual Registries turns complex API configurations into visual simplicity, providing a more intuitive experience for package administrators and platform engineers.\n\nPreviously, teams configured and maintained virtual registries only through API calls, which made routine maintenance time-consuming and required specialized platform knowledge. The new interface removes that barrier, helping to make everyday tasks faster and easier.\n\nWith this update, you can now:\n\n* Create virtual registries to simplify dependency configuration\n* Create and order upstreams to help improve performance and compliance\n* Browse and clear stale cache entries directly in the UI\n\nThis visual experience helps reduce operational overhead and provides development teams with clearer insight into how dependencies are resolved, enabling them to make better decisions about build performance and security policies.\n\nWatch a demo:\n\n\u003C!-- blank line -->\n\u003Cfigure class=\"video_container\">\n\u003Ciframe src=\"https://www.youtube.com/embed/CiOZJPhAvaI?si=cYaoR_OIgqFKbyM2\" frameborder=\"0\" allowfullscreen=\"true\"> \u003C/iframe>\n\u003C/figure>\n\u003C!-- blank line -->\n\n\u003Cp>\u003C/p>\n\nWe invite enterprise customers to join the [Maven Virtual Registry Beta program](https://gitlab.com/gitlab-org/gitlab/-/issues/543045) and share feedback to help shape the final release.\n\n## AI that adapts to your workflow\n\nThis release represents more than new capabilities — it's about choice and control. Watch the walkthrough video here:\n\n\u003Cp>\u003C/p>\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1128992281?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.5-tech-demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\u003Cp>\u003C/p>\n\nGitLab Premium and Ultimate users can start using these capabilities today on [GitLab.com](https://GitLab.com) and self-managed environments, with availability for GitLab Dedicated customers planned for next month.\n\nGitLab Duo Agent Platform is currently in **beta** — enable beta and experimental features to experience how full-context AI can transform the way your teams build software. New to GitLab? [Start your free trial](https://about.gitlab.com/free-trial/devsecops/) and see why the future of development is AI-powered, secure, and orchestrated through the world’s most comprehensive DevSecOps platform.\n\n***Note:** Platform capabilities that are in beta are available as part of the GitLab Beta program. They are free to use during the beta period, and when generally available, they will be made available with a paid add-on option for GitLab Duo Agent Platform.*\n\n### Stay up to date with GitLab\n\nTo make sure you’re getting the latest features, security updates, and performance improvements, we recommend keeping your GitLab instance up to date. The following resources can help you plan and complete your upgrade:\n\n* [Upgrade Path Tool](https://gitlab-com.gitlab.io/support/toolbox/upgrade-path/) – enter your current version and see the exact upgrade steps for your instance\n* [Upgrade Documentation](https://docs.gitlab.com/update/upgrade_paths/) – detailed guides for each supported version, including requirements, step-by-step instructions, and best practices\n\nBy upgrading regularly, you’ll ensure your team benefits from the newest GitLab capabilities and remains secure and supported.\n\nFor organizations that want a hands-off approach, consider [GitLab’s Managed Maintenance service](https://content.gitlab.com/viewer/d1fe944dddb06394e6187f0028f010ad#1). With Managed Maintenance, your team stays focused on innovation while GitLab experts keep your Self-Managed instance reliably upgraded, secure, and ready to lead in DevSecOps. Ask your account manager for more information.\n\n*This blog post contains \"forward‑looking statements\" within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934. Although we believe that the expectations reflected in these statements are reasonable, they are subject to known and unknown risks, uncertainties, assumptions and other factors that may cause actual results or outcomes to differ materially. Further information on these risks and other factors is included under the caption \"Risk Factors\" in our filings with the SEC. We do not undertake any obligation to update or revise these statements after the date of this blog post, except as required by law.*\n",{"config":31,"title":5,"description":17},{"noIndex":32},false,"en-us/blog/gitlab-18-5-intelligence-that-moves-software-development-forward",[21,22,35],"devsecops-platform",[21,22,23],"aUmtajeZEM6ETUkKCAPjOJCyaPbnfOTgN64irLEjeaE",{"logo":39,"freeTrial":44,"sales":49,"login":54,"items":59,"search":379,"minimal":410,"duo":429,"switchNav":438,"pricingDeployment":449},{"config":40},{"href":41,"dataGaName":42,"dataGaLocation":43},"/","gitlab logo","header",{"text":45,"config":46},"Get free trial",{"href":47,"dataGaName":48,"dataGaLocation":43},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":50,"config":51},"Talk to sales",{"href":52,"dataGaName":53,"dataGaLocation":43},"/sales/","sales",{"text":55,"config":56},"Sign in",{"href":57,"dataGaName":58,"dataGaLocation":43},"https://gitlab.com/users/sign_in/","sign in",[60,89,189,194,298,359],{"text":61,"config":62,"menu":64},"Platform",{"dataNavLevelOne":63},"platform",{"type":65,"columns":66},"cards",[67,73,81],{"title":61,"description":68,"link":69},"The intelligent orchestration platform for DevSecOps",{"text":70,"config":71},"Explore our Platform",{"href":72,"dataGaName":63,"dataGaLocation":43},"/platform/",{"title":74,"description":75,"link":76},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":77,"config":78},"Meet GitLab Duo",{"href":79,"dataGaName":80,"dataGaLocation":43},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":82,"description":83,"link":84},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":85,"config":86},"Learn more",{"href":87,"dataGaName":88,"dataGaLocation":43},"/why-gitlab/","why gitlab",{"text":90,"left":15,"config":91,"menu":93},"Product",{"dataNavLevelOne":92},"solutions",{"type":94,"link":95,"columns":99,"feature":168},"lists",{"text":96,"config":97},"View all Solutions",{"href":98,"dataGaName":92,"dataGaLocation":43},"/solutions/",[100,124,147],{"title":101,"description":102,"link":103,"items":108},"Automation","CI/CD and automation to accelerate deployment",{"config":104},{"icon":105,"href":106,"dataGaName":107,"dataGaLocation":43},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[109,113,116,120],{"text":110,"config":111},"CI/CD",{"href":112,"dataGaLocation":43,"dataGaName":110},"/solutions/continuous-integration/",{"text":74,"config":114},{"href":79,"dataGaLocation":43,"dataGaName":115},"gitlab duo agent platform - product menu",{"text":117,"config":118},"Source Code Management",{"href":119,"dataGaLocation":43,"dataGaName":117},"/solutions/source-code-management/",{"text":121,"config":122},"Automated Software Delivery",{"href":106,"dataGaLocation":43,"dataGaName":123},"Automated software delivery",{"title":125,"description":126,"link":127,"items":132},"Security","Deliver code faster without compromising security",{"config":128},{"href":129,"dataGaName":130,"dataGaLocation":43,"icon":131},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[133,137,142],{"text":134,"config":135},"Application Security Testing",{"href":129,"dataGaName":136,"dataGaLocation":43},"Application security testing",{"text":138,"config":139},"Software Supply Chain Security",{"href":140,"dataGaLocation":43,"dataGaName":141},"/solutions/supply-chain/","Software supply chain security",{"text":143,"config":144},"Software Compliance",{"href":145,"dataGaName":146,"dataGaLocation":43},"/solutions/software-compliance/","software compliance",{"title":148,"link":149,"items":154},"Measurement",{"config":150},{"icon":151,"href":152,"dataGaName":153,"dataGaLocation":43},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[155,159,163],{"text":156,"config":157},"Visibility & Measurement",{"href":152,"dataGaLocation":43,"dataGaName":158},"Visibility and Measurement",{"text":160,"config":161},"Value Stream Management",{"href":162,"dataGaLocation":43,"dataGaName":160},"/solutions/value-stream-management/",{"text":164,"config":165},"Analytics & Insights",{"href":166,"dataGaLocation":43,"dataGaName":167},"/solutions/analytics-and-insights/","Analytics and insights",{"title":169,"type":94,"items":170},"GitLab for",[171,177,183],{"text":172,"config":173},"Enterprise",{"icon":174,"href":175,"dataGaLocation":43,"dataGaName":176},"Building","/enterprise/","enterprise",{"text":178,"config":179},"Small Business",{"icon":180,"href":181,"dataGaLocation":43,"dataGaName":182},"Work","/small-business/","small business",{"text":184,"config":185},"Public Sector",{"icon":186,"href":187,"dataGaLocation":43,"dataGaName":188},"Organization","/solutions/public-sector/","public sector",{"text":190,"config":191},"Pricing",{"href":192,"dataGaName":193,"dataGaLocation":43,"dataNavLevelOne":193},"/pricing/","pricing",{"text":195,"config":196,"menu":198},"Resources",{"dataNavLevelOne":197},"resources",{"type":94,"link":199,"columns":203,"feature":287},{"text":200,"config":201},"View all resources",{"href":202,"dataGaName":197,"dataGaLocation":43},"/resources/",[204,237,259],{"title":205,"items":206},"Getting started",[207,212,217,222,227,232],{"text":208,"config":209},"Install",{"href":210,"dataGaName":211,"dataGaLocation":43},"/install/","install",{"text":213,"config":214},"Quick start guides",{"href":215,"dataGaName":216,"dataGaLocation":43},"/get-started/","quick setup checklists",{"text":218,"config":219},"Learn",{"href":220,"dataGaLocation":43,"dataGaName":221},"https://university.gitlab.com/","learn",{"text":223,"config":224},"Product documentation",{"href":225,"dataGaName":226,"dataGaLocation":43},"https://docs.gitlab.com/","product documentation",{"text":228,"config":229},"Best practice videos",{"href":230,"dataGaName":231,"dataGaLocation":43},"/getting-started-videos/","best practice videos",{"text":233,"config":234},"Integrations",{"href":235,"dataGaName":236,"dataGaLocation":43},"/integrations/","integrations",{"title":238,"items":239},"Discover",[240,245,250,254],{"text":241,"config":242},"Customer success stories",{"href":243,"dataGaName":244,"dataGaLocation":43},"/customers/","customer success stories",{"text":246,"config":247},"Blog",{"href":248,"dataGaName":249,"dataGaLocation":43},"/blog/","blog",{"text":251,"config":252},"The Source",{"href":253,"dataGaName":249,"dataGaLocation":43},"/the-source/",{"text":255,"config":256},"Remote",{"href":257,"dataGaName":258,"dataGaLocation":43},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":260,"items":261},"Connect",[262,267,272,277,282],{"text":263,"config":264},"GitLab Services",{"href":265,"dataGaName":266,"dataGaLocation":43},"/services/","services",{"text":268,"config":269},"Community",{"href":270,"dataGaName":271,"dataGaLocation":43},"/community/","community",{"text":273,"config":274},"Forum",{"href":275,"dataGaName":276,"dataGaLocation":43},"https://forum.gitlab.com/","forum",{"text":278,"config":279},"Events",{"href":280,"dataGaName":281,"dataGaLocation":43},"/events/","events",{"text":283,"config":284},"Partners",{"href":285,"dataGaName":286,"dataGaLocation":43},"/partners/","partners",{"config":288,"title":291,"text":292,"link":293},{"background":289,"textColor":290},"url('https://res.cloudinary.com/about-gitlab-com/image/upload/v1777322348/qpq8yrgn8knii57omj0c.png')","#000","What’s new in GitLab","Stay updated with our latest features and improvements.",{"text":294,"config":295},"Read the latest",{"href":296,"dataGaName":297,"dataGaLocation":43},"/releases/whats-new/","whats new",{"text":299,"config":300,"menu":302},"Company",{"dataNavLevelOne":301},"company",{"type":94,"columns":303},[304],{"items":305},[306,311,317,319,324,329,334,339,344,349,354],{"text":307,"config":308},"About",{"href":309,"dataGaName":310,"dataGaLocation":43},"/company/","about",{"text":312,"config":313,"footerGa":316},"Jobs",{"href":314,"dataGaName":315,"dataGaLocation":43},"/jobs/","jobs",{"dataGaName":315},{"text":278,"config":318},{"href":280,"dataGaName":281,"dataGaLocation":43},{"text":320,"config":321},"Leadership",{"href":322,"dataGaName":323,"dataGaLocation":43},"/company/team/e-group/","leadership",{"text":325,"config":326},"Team",{"href":327,"dataGaName":328,"dataGaLocation":43},"/company/team/","team",{"text":330,"config":331},"Handbook",{"href":332,"dataGaName":333,"dataGaLocation":43},"https://handbook.gitlab.com/","handbook",{"text":335,"config":336},"Investor relations",{"href":337,"dataGaName":338,"dataGaLocation":43},"https://ir.gitlab.com/","investor relations",{"text":340,"config":341},"Trust Center",{"href":342,"dataGaName":343,"dataGaLocation":43},"/security/","trust center",{"text":345,"config":346},"AI Transparency Center",{"href":347,"dataGaName":348,"dataGaLocation":43},"/ai-transparency-center/","ai transparency center",{"text":350,"config":351},"Newsletter",{"href":352,"dataGaName":353,"dataGaLocation":43},"/company/contact/#contact-forms","newsletter",{"text":355,"config":356},"Press",{"href":357,"dataGaName":358,"dataGaLocation":43},"/press/","press",{"text":360,"config":361,"menu":362},"Contact us",{"dataNavLevelOne":301},{"type":94,"columns":363},[364],{"items":365},[366,369,374],{"text":50,"config":367},{"href":52,"dataGaName":368,"dataGaLocation":43},"talk to sales",{"text":370,"config":371},"Support portal",{"href":372,"dataGaName":373,"dataGaLocation":43},"https://support.gitlab.com","support portal",{"text":375,"config":376},"Customer portal",{"href":377,"dataGaName":378,"dataGaLocation":43},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":380,"login":381,"suggestions":388},"Close",{"text":382,"link":383},"To search repositories and projects, login to",{"text":384,"config":385},"gitlab.com",{"href":57,"dataGaName":386,"dataGaLocation":387},"search login","search",{"text":389,"default":390},"Suggestions",[391,393,397,399,403,407],{"text":74,"config":392},{"href":79,"dataGaName":74,"dataGaLocation":387},{"text":394,"config":395},"Code Suggestions (AI)",{"href":396,"dataGaName":394,"dataGaLocation":387},"/solutions/code-suggestions/",{"text":110,"config":398},{"href":112,"dataGaName":110,"dataGaLocation":387},{"text":400,"config":401},"GitLab on AWS",{"href":402,"dataGaName":400,"dataGaLocation":387},"/partners/technology-partners/aws/",{"text":404,"config":405},"GitLab on Google Cloud",{"href":406,"dataGaName":404,"dataGaLocation":387},"/partners/technology-partners/google-cloud-platform/",{"text":408,"config":409},"Why GitLab?",{"href":87,"dataGaName":408,"dataGaLocation":387},{"freeTrial":411,"mobileIcon":416,"desktopIcon":421,"secondaryButton":424},{"text":412,"config":413},"Start free trial",{"href":414,"dataGaName":48,"dataGaLocation":415},"https://gitlab.com/-/trials/new/","nav",{"altText":417,"config":418},"Gitlab Icon",{"src":419,"dataGaName":420,"dataGaLocation":415},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":417,"config":422},{"src":423,"dataGaName":420,"dataGaLocation":415},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":425,"config":426},"Get Started",{"href":427,"dataGaName":428,"dataGaLocation":415},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":430,"mobileIcon":434,"desktopIcon":436},{"text":431,"config":432},"Learn more about GitLab Duo",{"href":79,"dataGaName":433,"dataGaLocation":415},"gitlab duo",{"altText":417,"config":435},{"src":419,"dataGaName":420,"dataGaLocation":415},{"altText":417,"config":437},{"src":423,"dataGaName":420,"dataGaLocation":415},{"button":439,"mobileIcon":444,"desktopIcon":446},{"text":440,"config":441},"/switch",{"href":442,"dataGaName":443,"dataGaLocation":415},"#contact","switch",{"altText":417,"config":445},{"src":419,"dataGaName":420,"dataGaLocation":415},{"altText":417,"config":447},{"src":448,"dataGaName":420,"dataGaLocation":415},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":450,"mobileIcon":455,"desktopIcon":457},{"text":451,"config":452},"Back to pricing",{"href":192,"dataGaName":453,"dataGaLocation":415,"icon":454},"back to pricing","GoBack",{"altText":417,"config":456},{"src":419,"dataGaName":420,"dataGaLocation":415},{"altText":417,"config":458},{"src":423,"dataGaName":420,"dataGaLocation":415},{"title":460,"button":461,"config":466},"See how agentic AI transforms software delivery",{"text":462,"config":463},"Sign up for GitLab Transcend on June 10",{"href":464,"dataGaName":465,"dataGaLocation":43},"/releases/whats-new/#sign-up","transcend event",{"layout":467,"icon":468,"disabled":32},"release","AiStar",{"data":470},{"text":471,"source":472,"edit":478,"contribute":483,"config":488,"items":493,"minimal":699},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":473,"config":474},"View page source",{"href":475,"dataGaName":476,"dataGaLocation":477},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":479,"config":480},"Edit this page",{"href":481,"dataGaName":482,"dataGaLocation":477},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":484,"config":485},"Please contribute",{"href":486,"dataGaName":487,"dataGaLocation":477},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":489,"facebook":490,"youtube":491,"linkedin":492},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[494,541,594,638,665],{"title":190,"links":495,"subMenu":510},[496,500,505],{"text":497,"config":498},"View plans",{"href":192,"dataGaName":499,"dataGaLocation":477},"view plans",{"text":501,"config":502},"Why Premium?",{"href":503,"dataGaName":504,"dataGaLocation":477},"/pricing/premium/","why premium",{"text":506,"config":507},"Why Ultimate?",{"href":508,"dataGaName":509,"dataGaLocation":477},"/pricing/ultimate/","why ultimate",[511],{"title":512,"links":513},"Contact Us",[514,517,519,521,526,531,536],{"text":515,"config":516},"Contact sales",{"href":52,"dataGaName":53,"dataGaLocation":477},{"text":370,"config":518},{"href":372,"dataGaName":373,"dataGaLocation":477},{"text":375,"config":520},{"href":377,"dataGaName":378,"dataGaLocation":477},{"text":522,"config":523},"Status",{"href":524,"dataGaName":525,"dataGaLocation":477},"https://status.gitlab.com/","status",{"text":527,"config":528},"Terms of use",{"href":529,"dataGaName":530,"dataGaLocation":477},"/terms/","terms of use",{"text":532,"config":533},"Privacy statement",{"href":534,"dataGaName":535,"dataGaLocation":477},"/privacy/","privacy statement",{"text":537,"config":538},"Cookie preferences",{"dataGaName":539,"dataGaLocation":477,"id":540,"isOneTrustButton":15},"cookie preferences","ot-sdk-btn",{"title":90,"links":542,"subMenu":550},[543,546],{"text":23,"config":544},{"href":72,"dataGaName":545,"dataGaLocation":477},"devsecops platform",{"text":547,"config":548},"AI-Assisted Development",{"href":79,"dataGaName":549,"dataGaLocation":477},"ai-assisted development",[551],{"title":552,"links":553},"Topics",[554,559,564,569,574,579,584,589],{"text":555,"config":556},"CICD",{"href":557,"dataGaName":558,"dataGaLocation":477},"/topics/ci-cd/","cicd",{"text":560,"config":561},"GitOps",{"href":562,"dataGaName":563,"dataGaLocation":477},"/topics/gitops/","gitops",{"text":565,"config":566},"DevOps",{"href":567,"dataGaName":568,"dataGaLocation":477},"/topics/devops/","devops",{"text":570,"config":571},"Version Control",{"href":572,"dataGaName":573,"dataGaLocation":477},"/topics/version-control/","version control",{"text":575,"config":576},"DevSecOps",{"href":577,"dataGaName":578,"dataGaLocation":477},"/topics/devsecops/","devsecops",{"text":580,"config":581},"Cloud Native",{"href":582,"dataGaName":583,"dataGaLocation":477},"/topics/cloud-native/","cloud native",{"text":585,"config":586},"AI for Coding",{"href":587,"dataGaName":588,"dataGaLocation":477},"/topics/devops/ai-for-coding/","ai for coding",{"text":590,"config":591},"Agentic AI",{"href":592,"dataGaName":593,"dataGaLocation":477},"/topics/agentic-ai/","agentic ai",{"title":595,"links":596},"Solutions",[597,599,601,606,610,613,617,620,622,625,628,633],{"text":134,"config":598},{"href":129,"dataGaName":134,"dataGaLocation":477},{"text":123,"config":600},{"href":106,"dataGaName":107,"dataGaLocation":477},{"text":602,"config":603},"Agile development",{"href":604,"dataGaName":605,"dataGaLocation":477},"/solutions/agile-delivery/","agile delivery",{"text":607,"config":608},"SCM",{"href":119,"dataGaName":609,"dataGaLocation":477},"source code management",{"text":555,"config":611},{"href":112,"dataGaName":612,"dataGaLocation":477},"continuous integration & delivery",{"text":614,"config":615},"Value stream management",{"href":162,"dataGaName":616,"dataGaLocation":477},"value stream management",{"text":560,"config":618},{"href":619,"dataGaName":563,"dataGaLocation":477},"/solutions/gitops/",{"text":172,"config":621},{"href":175,"dataGaName":176,"dataGaLocation":477},{"text":623,"config":624},"Small business",{"href":181,"dataGaName":182,"dataGaLocation":477},{"text":626,"config":627},"Public sector",{"href":187,"dataGaName":188,"dataGaLocation":477},{"text":629,"config":630},"Education",{"href":631,"dataGaName":632,"dataGaLocation":477},"/solutions/education/","education",{"text":634,"config":635},"Financial services",{"href":636,"dataGaName":637,"dataGaLocation":477},"/solutions/finance/","financial services",{"title":195,"links":639},[640,642,644,646,649,651,653,655,657,659,661,663],{"text":208,"config":641},{"href":210,"dataGaName":211,"dataGaLocation":477},{"text":213,"config":643},{"href":215,"dataGaName":216,"dataGaLocation":477},{"text":218,"config":645},{"href":220,"dataGaName":221,"dataGaLocation":477},{"text":223,"config":647},{"href":225,"dataGaName":648,"dataGaLocation":477},"docs",{"text":246,"config":650},{"href":248,"dataGaName":249,"dataGaLocation":477},{"text":241,"config":652},{"href":243,"dataGaName":244,"dataGaLocation":477},{"text":255,"config":654},{"href":257,"dataGaName":258,"dataGaLocation":477},{"text":263,"config":656},{"href":265,"dataGaName":266,"dataGaLocation":477},{"text":268,"config":658},{"href":270,"dataGaName":271,"dataGaLocation":477},{"text":273,"config":660},{"href":275,"dataGaName":276,"dataGaLocation":477},{"text":278,"config":662},{"href":280,"dataGaName":281,"dataGaLocation":477},{"text":283,"config":664},{"href":285,"dataGaName":286,"dataGaLocation":477},{"title":299,"links":666},[667,669,671,673,675,677,679,683,688,690,692,694],{"text":307,"config":668},{"href":309,"dataGaName":301,"dataGaLocation":477},{"text":312,"config":670},{"href":314,"dataGaName":315,"dataGaLocation":477},{"text":320,"config":672},{"href":322,"dataGaName":323,"dataGaLocation":477},{"text":325,"config":674},{"href":327,"dataGaName":328,"dataGaLocation":477},{"text":330,"config":676},{"href":332,"dataGaName":333,"dataGaLocation":477},{"text":335,"config":678},{"href":337,"dataGaName":338,"dataGaLocation":477},{"text":680,"config":681},"Sustainability",{"href":682,"dataGaName":680,"dataGaLocation":477},"/sustainability/",{"text":684,"config":685},"Diversity, inclusion and belonging (DIB)",{"href":686,"dataGaName":687,"dataGaLocation":477},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":340,"config":689},{"href":342,"dataGaName":343,"dataGaLocation":477},{"text":350,"config":691},{"href":352,"dataGaName":353,"dataGaLocation":477},{"text":355,"config":693},{"href":357,"dataGaName":358,"dataGaLocation":477},{"text":695,"config":696},"Modern Slavery Transparency Statement",{"href":697,"dataGaName":698,"dataGaLocation":477},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":700},[701,704,707],{"text":702,"config":703},"Terms",{"href":529,"dataGaName":530,"dataGaLocation":477},{"text":705,"config":706},"Cookies",{"dataGaName":539,"dataGaLocation":477,"id":540,"isOneTrustButton":15},{"text":708,"config":709},"Privacy",{"href":534,"dataGaName":535,"dataGaLocation":477},[711],{"id":712,"title":9,"body":26,"config":713,"content":715,"description":26,"extension":719,"meta":720,"navigation":15,"path":721,"seo":722,"stem":723,"__hash__":724},"blogAuthors/en-us/blog/authors/bill-staples.yml",{"template":714},"BlogAuthor",{"name":9,"config":716,"role":718},{"headshot":717},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1750434080/glxv59lh9qftpdbsb4ph.png","CEO","yml",{},"/en-us/blog/authors/bill-staples",{},"en-us/blog/authors/bill-staples","K-ulWVa7KOFAxgiGSmeiIjz3KeQyIkhm95lIRX_r6Zc",[726,739,751],{"content":727,"config":737},{"title":728,"description":729,"authors":730,"date":732,"heroImage":733,"body":734,"category":11,"tags":735},"Atlassian will train on your data: Opt out with GitLab","Learn why Atlassian's latest move is a threat to data governance and how GitLab's approach helps ensure your customers' data stays private and protected.",[731],"Jessica Hurwitz","2026-05-04","https://res.cloudinary.com/about-gitlab-com/image/upload/v1773866173/vte9qh8rriznvyclhkes.png","Starting August 17, 2026, Atlassian will begin collecting customer metadata and in-app content from Jira, Confluence, and other cloud products to train its AI offerings, including Rovo and Rovo Dev. This announcement comes after [GitHub recently changed its Copilot data usage policy](https://about.gitlab.com/blog/github-copilots-new-policy-for-ai-training-is-a-governance-wake-up-call/). **Taken together, these changes suggest opt-out-by-default is becoming the industry norm. GitLab takes the opposite position: no data collection, no AI training on customer data, no matter what tier you're on.**\n\n[Atlassian's change](https://www.atlassian.com/trust/ai/data-contribution) is enabled by default for all cloud customers and affects roughly 300,000 organizations. For customers on the Free, Standard, and Premium tiers, metadata collection is mandatory and cannot be turned off. Only Enterprise-tier customers have the option to opt out. This policy change deserves a close read if your engineering, IT, and program management teams run on Atlassian because they are most exposed by this change — and least likely to have been consulted before it happened.\n\nAlthough the underlying governance questions are the same for both Atlassian and GitHub's changes, the data at risk is different. Where GitHub's change concerned source code and developer interactions, Atlassian's reaches into project plans, internal documentation, workflow configurations, and operational metadata across Jira, Confluence, and the broader Atlassian stack. **For organizations that rely on these tools as their system of record for how work gets planned and delivered, the implications run deep.**\n\n## What changed and what it means for your data\n\nAtlassian will collect two categories of information: \n\n- **Metadata:** de-identified operational signals like story points, sprint dates, and SLA values, including data from its Teamwork Graph and connected third-party apps  \n- **In-app content:** user-generated material such as Confluence page content, Jira issue titles, descriptions, and comments\n\nAtlassian says it will apply de-identification and aggregation before training. Collected data may be retained for up to seven years, with in-app data removed within 30 days of opt-out and models retrained within 90 days.\n\nThere are some exclusions: Customers using customer-managed encryption keys, Atlassian Government Cloud, Isolated Cloud, or those with HIPAA requirements are carved out from collection. But for the vast majority of Atlassian's cloud customer base, data collection will start unless you pay for the Enterprise tier and actively flip the switch.\n\nThis reverses Atlassian's prior stated position that customer data would not be used to train or improve AI services. Organizations that adopted Jira and Confluence to manage their most sensitive planning workflows, sprint boards, security tickets, incident postmortems, and internal documentation will soon be contributing that content to Atlassian's AI training pipeline, without ever being asked.\n\n## The governance gap in \"opt-out by default\"\n\nOpt-out-by-default data collection for AI training is an emerging pattern across the software industry. It raises the same set of questions every time: How does this interact with existing data processing agreements? Does the vendor's definition of \"metadata\" match what your legal and security teams would consider non-sensitive data?\n\n**For many organizations, the answer to these questions is \"we don't know.\"** \n\nWhen a vendor changes its data practices through a terms-of-service update, the burden falls on the customer to notice, evaluate the implications, and act within the window the vendor provides. \n\nThe mandatory nature of metadata collection on Free, Standard, and Premium tiers makes this more acute. The only exit is upgrading to Enterprise, which requires a minimum of 801 users and custom pricing that would represent a significant cost jump for teams that aren't there yet. Data protection, in other words, is now a purchasing decision.\n\nThe tiered structure also introduces a subtler problem. Metadata like story points, sprint velocity, SLA metrics, and task classifications may seem innocuous in isolation, but in aggregate they reveal project structure, team performance patterns, and delivery cadence. For organizations in competitive industries, that operational intelligence has real value, and \"de-identified\" does not necessarily mean \"non-sensitive\" once patterns are reconstructable at scale.\n\n## Why this matters more for Atlassian-stack organizations\n\nIn Atlassian-based organizations, Jira has been the center how teams plan, track, and deliver work. It’s the source of truth for sprint planning, bug tracking, release management, portfolio coordination, and cross-functional project execution. \n\nIn regulated industries like financial services, public sector and manufacturing, Jira and Confluence together hold sensitive operational data that may be subject to compliance requirements. The risk compounds for organizations that have expanded beyond Jira into the broader Atlassian ecosystem.\n\nWhen you run Jira, Confluence, Bitbucket, and Bamboo together, the surface area of data now feeding into AI training spans your project plans, internal documentation, source code metadata, and CI/CD configurations — each of which security and compliance teams would want to review before sharing with a vendor's training pipeline.\n\nAtlassian’s Teamwork Graph connectors add another dimension for customers who have integrated third-party tools, such as Slack, Figma, Google Drive, Salesforce, and ServiceNow, into their environment. Teamwork Graph connectors index relationship and activity signals from these connected apps, which means the metadata Atlassian collects will not be limited to what lives inside Atlassian products. For security and compliance teams accustomed to evaluating data flows on a per-vendor basis, this cross-platform reach complicates the assessment considerably.\n\nOrganizations that are already navigating [Atlassian's push from Data Center](https://about.gitlab.com/blog/atlassian-ending-data-center-as-gitlab-maintains-deployment-choice/) and Server editions to the cloud face a compounding challenge. Adding default AI data collection to that migration path raises the stakes further: **The question is no longer just \"do we move to Atlassian Cloud?\" but \"do we move to Atlassian Cloud knowing our data will feed AI training unless we're on the most expensive tier?\"**\n\n## What regulated industries should be evaluating now\n\nThe compliance implications vary by sector, but the obligation to reassess is consistent.\n\nIn financial services, frameworks like [SR 11-7](https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm) and [DORA](https://eur-lex.europa.eu/eli/reg/2022/2554/oj/eng) require documented, auditable oversight of third-party technology providers, including how those providers handle data. In the public sector, [NIST 800-53](https://csrc.nist.gov/publications/detail/sp/800-53/rev-5/final) and [FISMA](https://www.cisa.gov/topics/cyber-threats-and-advisories/federal-information-security-modernization-act) make controlling where sensitive data flows a foundational requirement. In healthcare, [HIPAA](https://www.hhs.gov/hipaa/index.html) governs how patient-adjacent data is handled by third parties. \n\nAcross the board, a material change in a vendor's data practices, such as Atlassian moving from \"we don't train on your data\" to \"we do, by default,\" triggers a documentation and risk reassessment obligation. \n\nInstitutions operating under the [EU AI Act](https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng) face an additional dimension: opt-out framing aligns with U.S. norms, while European regulators generally expect opt-in consent for data processing of this nature.\n\nIf your model risk or vendor management team documented Atlassian's data handling controls before this announcement, the question isn't whether this change triggers a reassessment obligation. It does. The question is whether your team can take action before August 17.\n\n## What to look for in your platform vendors\n\nCTOs and CISOs across regulated industries need to adopt AI in a way they can explain to regulators, boards, and customers. Because of this, GitLab operates within the following set of principles:\n\n**Unconditional data commitments, not tier-dependent protections.** Regulated organizations need to know, with specificity, what happens to their data. A commitment that varies by plan tier, or that requires action before a deadline, introduces exactly the kind of uncontrolled variable that keeps CISOs up at night.\n\n**Transparency and auditability.** Model risk management frameworks require organizations to understand the AI systems they deploy, including the training data and third parties involved. Vendors who cannot answer these questions clearly create documentation risk.\n\n**Separation between customer data and vendor AI training.** When a platform vendor trains models on customer usage data, workflows and operational patterns become inputs to a system that also serves competitors. For organizations where project structure or delivery cadence represents competitive advantage, that exposure matters.\n\n## How GitLab's approach differs\n\nGitLab doesn't train on customer data — at any tier, full stop. AI vendors powering GitLab Duo features are contractually prohibited from using customer inputs or outputs for their own purposes, [a commitment GitLab CEO Bill Staples](https://www.linkedin.com/posts/williamstaples_gitlab-1810-agentic-ai-now-open-to-even-activity-7443280763715985408-aHxf) has consistently reiterated.\n\n[GitLab's AI Transparency Center](https://about.gitlab.com/ai-transparency-center/) documents exactly which models power which features, how data is handled, and what vendor commitments are in place. [GitLab's AI Continuity Plan](https://handbook.gitlab.com/handbook/product/ai/continuity-plan/) documents how vendor changes are managed, including any material changes to how AI vendors treat customer data. For institutions managing third-party AI risk under DORA or similar frameworks, vendor continuity and concentration are active governance concerns, and having a documented plan for both is part of what responsible AI tooling looks like.\n\nFor organizations that require AI processing to stay within their own infrastructure, [GitLab Duo Agent Platform](https://about.gitlab.com/gitlab-duo/) is available with GitLab Self-Managed deployments, including support for integration with self-hosted AI models. This means prompts and code never leave the customer's environment. GitLab also provides IP indemnification for Duo-generated output, with no filters required and no activation steps needed. Where your data lives remains your choice, no matter your deployment model or subscription tier.\n\n> Whether your organization stays on Atlassian or begins evaluating alternatives, the conversation about who controls your data and how it gets used should be happening now. **The August 17 deadline is approaching, but you still have time to [try GitLab Ultimate with Duo Agent Platform for free today](https://gitlab.com/-/trials/new).**",[736,22],"AI/ML",{"featured":15,"template":13,"slug":738},"atlassian-will-train-on-your-data-opt-out-with-gitlab",{"content":740,"config":749},{"title":741,"description":742,"authors":743,"heroImage":745,"date":746,"body":747,"category":11,"tags":748},"GitLab and Anthropic: Governed AI for enterprise development","GitLab deepens its Anthropic Claude integration, bringing governed AI, access to new models, and cloud flexibility to enterprise software development.",[744],"Stuart Moncada","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776457632/llddiylsgwuze0u1rjks.png","2026-04-28","For enterprise and public sector leaders, the tension is familiar: Software teams need to move faster with AI, while security, compliance, and regulatory expectations only get more stringent. GitLab deepens its Anthropic Claude integration so organizations get access to newly released Claude models inside GitLab’s intelligent orchestration platform where governance, compliance, and auditability already run.\n\nClaude powers capabilities across GitLab Duo Agent Platform as the default model out of the box, across a variety of use cases from code generation and review to agentic chat and vulnerability resolution. If you've used GitLab Duo, you've already experienced how Duo agents automate workflows across the entire software development lifecycle (SDLC).\n\nThis accelerates the integration of Claude’s capabilities into GitLab, broadens how enterprises can deploy them, and reinforces what makes GitLab fundamentally different as a platform for software development and engineering: governance, compliance, and auditability built into every AI interaction.\n\n> \"GitLab Duo has accelerated how our teams plan, build, and ship software. The combination of Anthropic's Claude and GitLab's platform means we're getting more capable AI without changing how we work or how it is governed.\"\n>\n> – Mans Booijink, Operations Manager, Cube\n\n## The real differentiator: Governed AI\n\nWith GitLab, governance controls and auditing are built into the SDLC. When Claude suggests a code change through the GitLab Duo Agent Platform, that suggestion flows through the same merge request process, the same approval rules, the same security scanning, and the same audit trail as every other change. AI doesn't get a shortcut around your controls. It operates within them.\n\nAs GitLab moves deeper into agentic software development, where AI autonomously handles well-defined tasks, the governance layer becomes more important. An AI agent that can open a merge request, help resolve a vulnerability, or refactor a service needs to be auditable, attributable, and subject to the same policy enforcement as a human developer. That requirement is an architectural decision GitLab made from the start, and one that grows more consequential as AI agents take on broader responsibilities.\n\n## Enterprise deployment flexibility\n\nThis also expands how organizations access the latest Claude models through GitLab. Claude is available within GitLab through Google Cloud's Vertex AI and Amazon Bedrock, which means enterprises can route AI workloads through the hyperscaler commitments and cloud governance frameworks they already have in place. No separate vendor contract. No new data residency questions. Your existing Google Cloud or AWS relationship is the on-ramp. \n\nGitLab is now also available in the [Claude Marketplace](https://claude.com/platform/marketplace), allowing customers to purchase GitLab Credits and apply them toward existing Anthropic spending commitments – consolidating AI spend and simplifying how teams discover and procure GitLab alongside their Anthropic investments.\n\n## Advancing an agentic future\n\nGitLab's vision for agentic software development, where AI handles defined tasks autonomously across planning, coding, testing, securing, and deploying, requires models with strong reasoning, reliability, and safety characteristics. It also requires a platform where those autonomous actions are fully governed.\n\nAgentic workflows demand models with strong reasoning, reliability, and safety characteristics, criteria that guide how GitLab selects and integrates AI model partners. And GitLab's governance framework helps ensure that as AI agents assume more advanced development work, enterprises maintain full visibility and control over what those agents do, when they do it, and how changes are tracked.\n\n## What this means for GitLab customers\n\nIf you're already using GitLab Duo Agent Platform, you'll get access to Claude models and deeper AI assistance across your software development lifecycle, all within the governance framework you already rely on.\n\nIf you're evaluating AI-powered software development platforms, you shouldn't have to choose between advanced AI capabilities and enterprise control. This strategic integration is built to deliver both.\n\n> Want to learn more about GitLab Duo Agent Platform? [Get a demo or start a free trial today](https://about.gitlab.com/gitlab-duo-agent-platform/).",[736,22,286],{"featured":15,"template":13,"slug":750},"gitlab-and-anthropic-governed-ai-for-enterprise-development",{"content":752,"config":762},{"title":753,"description":754,"authors":755,"heroImage":757,"date":758,"body":759,"category":11,"tags":760},"Give your AI agent direct, structured GitLab access with glab CLI","The GitLab CLI (glab) provides AI agents structured, reliable access to projects via the MCP, eliminating friction. This tutorial shows how you can speed up code review and issue triage.",[756],"Kai Armstrong","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776347152/unw3mzatkd5xyfbzcnni.png","2026-04-27","\nWhen teams use GitLab Duo, Claude, Cursor, and other AI assistants, more of the development workflow runs through an AI agent acting on your behalf — reading issues, reviewing merge requests, running pipelines, and helping you ship faster. Most developers are already using the GitLab CLI (`glab`) from the terminal to interact with GitLab. Combining the two is a natural next step.\n\n\nThe problem is that without the right tools, AI agents are essentially guessing when it comes to your GitLab projects. They might hallucinate the details of an issue they've never seen, summarize a merge request based on stale training data rather than its actual state, or require you to manually copy context from a browser tab and paste it into a chat window just to get started. Every one of those workarounds is friction: it slows you down, introduces the possibility of error, and puts a hard ceiling on what your agent can actually do on your behalf. `glab` changes that by giving agents a direct, reliable interface to your projects.\n\n\nWith `glab`, your agent fetches what it needs directly from GitLab, acts on it, and reports back — so you spend less time relaying information and more time on the work that matters.\n\n\nIn this tutorial, you'll learn how to use `glab` to give AI agents structured, reliable access to your GitLab projects. You'll also discover how that unlocks a faster, more capable development workflow.\n\n\n## How to connect your AI agent to GitLab through MCP\n\n\nThe most direct way to supercharge your AI workflow is to give your AI agent native access to `glab` through Model Context Protocol ([MCP](https://about.gitlab.com/topics/ai/model-context-protocol/)).\n\n\n MCP is an open standard that lets AI tools discover and use external capabilities at runtime. Once connected, your AI assistant can read issues, comment on merge requests, check pipeline status, and write back to GitLab, all without copying anything from the UI or writing a single API call yourself.\n\n\n To get started, run:\n\n\n ```shell\n # Start the glab MCP server\n glab mcp serve\n ```\n\n\n Once your MCP client is configured, your AI can answer questions like *\"What's the status of my open MRs?\"* or *\"Are there any failing pipelines on main?\"* by querying GitLab directly, not scraping the web UI, not relying on stale training data. See the [full setup docs](https://docs.gitlab.com/cli/) for configuration steps for Claude Code, Cursor, and other editors.\n\n\n One detail worth knowing: `glab` automatically adds `--output json` when invoked through MCP, for any command that supports it. Your agent gets clean, structured data without you needing to think about output formats. And because `glab` uses the official MCP SDK, it stays compatible as the\n protocol evolves.\n\n\n We've also been deliberate about *which* commands are exposed through MCP. Commands that require interactive terminal input are intentionally\n excluded, so your agent never gets stuck waiting for input that will never come. What's exposed is what actually works reliably in an agent context.\n\n\n ## Let your AI participate in code review\n\n\n Most developers have a backlog of MRs waiting for review. It's one of the most time-consuming parts of the job and one of the best places to put\n AI to work. With `glab`, your agent doesn't just observe your review queue, it can work through it with you.\n\n\n ### See exactly what still needs addressing\n\n\n Start with this:\n\n\n ```shell\n glab mr view 2677 --comments --unresolved --output json\n ```\n\n\n This input returns the full MR: metadata, description, and every\n unresolved discussion, as a single structured JSON payload. Hand that to\n your AI and it has everything it needs: which threads are open, what the\n reviewer asked for, and in what context. No tab-switching, no copy-pasting\n individual comments.\n\n\n \n ```json\n {\n   \"id\": 2677,\n   \"title\": \"feat: add OAuth2 support\",\n   \"state\": \"opened\",\n   \"author\": { \"username\": \"jdwick\" },\n   \"labels\": [\"backend\", \"needs-review\"],\n   \"blocking_discussions_resolved\": false,\n   \"discussions\": [\n     {\n       \"id\": \"3107030349\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"dmurphy\" },\n           \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n           \"created_at\": \"2026-03-14T09:23:11.000Z\"\n         }\n       ]\n     },\n     {\n       \"id\": \"3107030412\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"sreeves\" },\n           \"body\": \"Token refresh logic needs a test for the expired token case\",\n           \"created_at\": \"2026-03-14T10:05:44.000Z\"\n         }\n       ]\n     }\n   ]\n }\n ```\n\n\n Instead of reading through every thread yourself, you ask your agent  *\"what do I still need to fix in MR 2677?\"* and get back a prioritized summary with suggested changes. This all happens from a single command.\n\n\n ### Close the loop programmatically\n\n\n Once your AI has helped you address the feedback, it can resolve\n discussions:\n\n\n ```shell\n # List all discussions — structured, ready for the agent to process\n glab mr note list 456 --output json\n\n # Resolve a discussion once the feedback is addressed\n glab mr note resolve 456 3107030349\n\n # Reopen if something needs another look\n glab mr note reopen 456 3107030349\n ```\n\n\n\n ```json\n [\n   {\n     \"id\": 3107030349,\n     \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n     \"author\": { \"username\": \"dmurphy\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   },\n   {\n     \"id\": 3107030412,\n     \"body\": \"Token refresh logic needs a test for the expired token case\",\n     \"author\": { \"username\": \"sreeves\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   }\n ]\n ```\n\n\n\n Note IDs are visible directly in the GitLab UI and API, no extra lookup needed. Your agent can work through the full list, verify each fix, and\n resolve as it goes.\n\n\n ## Talk to your AI about your code more effectively\n\n\n Even if you're not running an MCP server, there's a simpler shift that makes a huge difference: using `glab` to feed your AI better information.\n\n\n Think about the last time you asked an AI assistant to help triage issues or debug a failing pipeline. You probably copied some text from the GitLab UI and pasted it into the chat. Here's what your agent is actually\n working with when you do that:\n\n\n ```text\n open issues: 12 • milestone: 17.10 • label: bug, needs-triage ...\n ```\n\n\n Compare that to what it gets with `glab`:\n\n\n \n ```json\n [\n   {\n     \"iid\": 902,\n     \"title\": \"Pipeline fails on merge to main\",\n     \"labels\": [\"bug\", \"needs-triage\"],\n     \"milestone\": { \"title\": \"17.10\" },\n     \"assignees\": []\n   },\n   ...\n ]\n ```\n\n\n Structured, typed, complete; no ambiguity, no parsing guesswork. That's the difference between an agent that can act and one that has to ask\n follow-up questions.\n\n\n If you're using the MCP server, you get this automatically: `glab` adds `--output json` for any command that supports it. If you're working directly\n from the terminal, just add the flag yourself:\n\n\n ```shell\n # Pull open issues for triage\n glab issue list --label \"needs-triage\" --output json\n\n # Check pipeline status\n glab ci status --output json\n\n # Get full MR details\n glab mr view 456 --output json\n ```\n\n\n We've significantly expanded JSON output support in recent releases. It now covers CI status, milestones, labels, releases, schedules, cluster agents, work items, MR approvers, repo contributors, and more. If `glab` can\n retrieve it, your AI can consume it cleanly.\n\n\n ### A real workflow\n\n\n ```shell\n $ glab issue list --label \"needs-triage\" --milestone \"17.10\"\n --output json\n ```\n\n\n ```text\n Agent: I found 2 unassigned bugs in the 17.10 milestone that need triage:\n 1. #902 — Pipeline fails on merge to main (opened 5 days ago)\n 2. #903 — Auth token not refreshing on expiry (opened 4 days ago)\n Both are unassigned. Want me to draft triage notes and suggest assignees based on recent commit history?\n ```\n\n\n ## Your agent is never limited to built-in commands\n\n\n `glab`'s first-class commands cover the most common workflows, but your agent is never limited to them. Through `glab api`, it has authenticated access to the full GitLab REST and GraphQL API surface, using the same session, with no extra credentials or configuration required.\n\n\n This is a meaningful differentiator. Most CLI tools stop at what their commands expose. With `glab`, if GitLab's API supports it, your agent can do it. It's always working from a trusted, authenticated context.\n\n\n A practical example: fetching just the list of changed files in an MR before deciding which diffs to pull in full:\n\n\n ```shell\n # Get changed file paths — lightweight, no diff content yet\n glab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n | jq '.[].new_path'\n\n# Then fetch only the specific file your agent needs\nglab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n| jq '.[] | select(.new_path == \"path/to/file.go\")'\n ```\n\n\n ```text\n \"internal/auth/token.go\"\n \"internal/auth/token_test.go\"\n \"internal/oauth/refresh.go\"\n ```\n\n\n For anything the REST API doesn't cover (epics, certain work item queries, complex cross-project data),  `glab api graphql` gives you the full\n GraphQL interface:\n\n\n ```shell\n   glab api graphql -f query='\n {\n   project(fullPath: \"gitlab-org/gitlab\") {\n     mergeRequest(iid: \"12345\") {\n       title\n       reviewers { nodes { username } }\n     }\n   }\n }'\n ```\n\n ```json\n{\n   \"data\": {\n     \"project\": {\n       \"mergeRequest\": {\n         \"title\": \"feat: add OAuth2 support\",\n         \"reviewers\": {\n           \"nodes\": [\n             { \"username\": \"dmurphy\" },\n             { \"username\": \"sreeves\" }\n           ]\n         }\n       }\n     }\n   }\n }\n\n ```\n\n\n Your agent has a single, authenticated entry point to everything GitLab exposes without the token juggling, separate API clients, or configuration\n overhead.\n\n\n ## What's coming and your feedback\n\n\n Two improvements we're actively working on will make `glab` even more useful for agent workflows:\n\n\n **Agent-aware help text.** Today, `--help` output is written for humansvat a terminal. We're updating it to surface the non-interactive alternative\n for every interactive command, flag which commands support `--output json`, and generally make help a useful resource for agents discovering\n capabilities at runtime — not just humans.\n\n\n **Better machine-readable errors.** When something goes wrong today, agents get the same human-readable error messages as terminal users. We're\n changing that so errors in JSON mode return structured output, giving your agent the information it needs to handle failures gracefully, retry intelligently, or surface the right context back to you.\n\n\n Both of these are in active development. If you're already using `glab` with an AI tool, you're exactly the audience we want feedback from.\n\n\n * **What friction are you hitting?** Commands that don't behave well in agent contexts, error messages that aren't actionable, gaps in JSON output\n coverage. We want to know.\n\n * **What workflows have you unlocked?** Real usage patterns help us prioritize what to build next.\n\n\n Join the discussion in [our feedback issue](https://gitlab.com/gitlab-org/cli/-/issues/8177) — that's where we're shaping the roadmap for agent-friendliness, and where your input will have the most direct impact. If you've found a specific gap, [open an issue](https://gitlab.com/gitlab-org/cli/-/issues/new). If you've got a fix in mind, contributions are welcome. Visit [CONTRIBUTING.md](https://gitlab.com/gitlab-org/cli/-/blob/main/CONTRIBUTING.md) to get started.\n\n\n The GitLab CLI has always been about giving developers more control over their workflow. As AI becomes a bigger part of how we all work, that means making `glab` the best possible interface between your AI tools and your GitLab projects. We're just getting started and we'd love to build the next part with you.\n",[736,22,761],"tutorial",{"featured":15,"template":13,"slug":763},"give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"promotions":765},[766,779,790,802],{"id":767,"categories":768,"header":769,"text":770,"button":771,"image":776},"ai-modernization",[11],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":772,"config":773},"Get your AI maturity score",{"href":774,"dataGaName":775,"dataGaLocation":249},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":777},{"src":778},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":780,"categories":781,"header":782,"text":770,"button":783,"image":787},"devops-modernization",[22,578],"Are you just managing tools or shipping innovation?",{"text":784,"config":785},"Get your DevOps maturity score",{"href":786,"dataGaName":775,"dataGaLocation":249},"/assessments/devops-modernization-assessment/",{"config":788},{"src":789},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":791,"categories":792,"header":794,"text":770,"button":795,"image":799},"security-modernization",[793],"security","Are you trading speed for security?",{"text":796,"config":797},"Get your security maturity score",{"href":798,"dataGaName":775,"dataGaLocation":249},"/assessments/security-modernization-assessment/",{"config":800},{"src":801},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":803,"paths":804,"header":807,"text":808,"button":809,"image":814},"github-azure-migration",[805,806],"migration-from-azure-devops-to-gitlab","integrating-azure-devops-scm-and-gitlab","Is your team ready for GitHub's Azure move?","GitHub is already rebuilding around Azure. Find out what it means for you.",{"text":810,"config":811},"See how GitLab compares to GitHub",{"href":812,"dataGaName":813,"dataGaLocation":249},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":815},{"src":789},{"header":817,"blurb":818,"button":819,"secondaryButton":824},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":820,"config":821},"Get your free trial",{"href":822,"dataGaName":48,"dataGaLocation":823},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":515,"config":825},{"href":52,"dataGaName":53,"dataGaLocation":823},1777934828967]