GitLab Announces Public Beta of GitLab Duo Agent Platform

GitLab Inc., the most comprehensive, intelligent DevSecOps platform, recently announced the public beta launch of GitLab Duo Agent Platform, a DevSecOps orchestration platform designed to unlock asynchronous collaboration between developers and Artificial Intelligence (AI) agents.

“This release marks a pivotal moment in software development as we introduce the public beta of the GitLab Duo Agent Platform, the first DevSecOps orchestration platform designed to unlock asynchronous collaboration between developers and AI agents,” said Bill Staples, CEO at GitLab. “GitLab Duo Agent Platform isn’t just another AI tool; it’s a fundamental reimagining of software development from isolated, linear processes into dynamic, intelligent collaboration. By leveraging GitLab’s unique position as the system of record for the entire software development lifecycle, we’re providing AI agents with unprecedented context and capabilities. This enables our customers to work with AI agents that have comprehensive context about their codebase, their workflows, and their organisational goals to help boost productivity, velocity, and efficiency.”

GitLab Duo Agent Platform represents a significant advancement in software development by establishing an intelligent orchestration layer that facilitates seamless collaboration between specialised AI agents and human developers. Leveraging GitLab’s role as the system of record for software development, the platform equips AI agents with comprehensive project context, enabling informed decisions that align with organisational standards.

GitLab Duo Agent Platform Capabilities Available Now in Public Beta

The first capabilities for GitLab Duo Agent Platform in public beta, now available to Premium and Ultimate customers, include:

• Software Development Flow: The first orchestrated multi-agent workflow that gathers comprehensive context, clarifies ambiguities with developers, and executes strategic plans to make precise changes to codebases and repositories, leveraging the project structure, codebase, and history along with additional context like GitLab issues or merge requests.
• GitLab Duo Agentic Chat in IDE: Transforms the chat experience from a passive Q&A tool into an active development partner directly in development environments, enabling more sophisticated interactions and task delegation through enhanced capabilities, including:
• Iterative Feedback and Chat History: Enables Duo Agentic Chat to support stateful, conversational partnerships that help foster trust and enable developers to delegate more complex tasks with corrective guidance.
• Streamlined Delegation Through Slash Commands: Expanded commands such as /explain, /tests, and /include that create a “delegation language” for quick and precise intent, with /include allowing explicit context injection from specific files, issues, merge requests, or dependencies.
• Personalisation Through Custom Rules: Enables developers to tailor agent behavior to individual and team preferences using natural language for development style guides and organisational policies.
  • GitLab Duo Agentic Chat in Web UI: Provides direct access within the GitLab Web UI, evolving the agent from a coding assistant to a true DevSecOps agent with access to rich non-code context and the ability to make changes directly from the Web UI.
  • JetBrains IDEs Support: Expands Duo Agentic Chat to the JetBrains family of IDEs, including IntelliJ, PyCharm, GoLand, and WebStorm, with automatic agentic capabilities for existing users and marketplace installation for new users.
  • Model Context Protocol (MCP) Client Support: Enables Duo Agentic Chat to connect to remote and locally running MCP servers, allowing connections to systems beyond GitLab with any service that exposes itself via MCP, becoming part of the agent’s skill set.

“As software development workflows grow in complexity and organisations look to leverage AI, there’s an increasing need for platforms that can integrate AI capabilities without adding to existing disjointed toolchains,” said Rachel Stephens, Research Director at RedMonk. “As a DevSecOps platform, GitLab is already positioned to help developers collaborate both synchronously and asynchronously. Now the GitLab Duo Agent Platform intends to take this a step further, helping developers also integrate AI agents into their workflows.”

Each month, GitLab plans to increase the scope and quality of the GitLab Duo Agent Platform in subsequent 18.x releases, with a target for general availability by the end of the year. To learn more about GitLab Duo Agent Platform capabilities and product roadmap, read the GitLab blog.