What programming languages does GitLab Duo Agent Platform support?

The best results for code generation are expected for languages the Google Vertex AI Codey APIs directly support: C++, C#, Go, Google SQL, Java, JavaScript, Kotlin, PHP, Python, Ruby, Rust, Scala, Swift, and TypeScript.

How does credit consumption work?

Credits are drawn down based on the number of agentic requests made, with different rates depending on which large language model is used. For example, you get two model requests per credit for Claude-sonnet-4 (the default for most features), and 20 requests per credit for models like gpt-5-mini or claude-3-haiku. For more details on GitLab Credits, please see here.

GitLab DuoAn AI-powered suite enhancing the software development lifecycle with intelligent assistance and automation.

4.3 (4)

Reviewed by Daniel Nikulshyn·Updated June 2026

AI Assistant DevOps Software Development Automation Enterprise Code Generation CI/CD Productivity

Overview

GitLab Duo is an AI-powered suite that enhances the software development lifecycle with intelligent assistance and automation. It allows teams to search and utilize specialized agents designed for planning, coding, security analysis, analytics, and more. Each agent uses GitLab context to deliver precise, relevant results that support real work. The platform also includes customizable assistance, a centralized AI catalog, and agentic workflows to automate complex tasks. Teams can create or refine agents to follow their conventions and mirror their quality expectations. The platform also integrates external agents such as Claude Code and Codex into the GitLab workflow. It enables event-driven execution, providing reliable and repeatable automation. Additionally, it offers enterprise-grade governance and control, with clear permissions, boundaries, and transparency. Teams can track flow sessions and utilize self-hosted models in alignment with their compliance requirements. The platform is extensible and flexible by design, allowing teams to adapt it to their existing environment. Agents and flows can be updated, extended, or replaced over time, helping teams evolve their AI strategy. The platform is powered by GitLab Orbit, a lifecycle context graph that natively supports the Duo Agent Platform and software development agents. GitLab Duo has endless use cases, from specialized agents that understand security posture to automated flows that eliminate manual handoffs. It provides a centralized place to explore, activate, and manage agents and flows, making new automation simple to adopt and consistent to operationalize across projects and groups.

Key features

Agent platform with customizable assistance and a centralized AI catalog
Agentic workflows for automating complex tasks
Event-driven execution for reliable and repeatable automation
Enterprise-grade governance and control with clear permissions and transparency
Integration with external agents and tools
Self-hosted models with compliance requirements

Pricing

Model: Freemium
Category: AI security
Rating: 4.3 / 5 (4)

Use cases

AI-Assisted Code Generation

Help developers write code faster by providing intelligent code suggestions and completions directly within the GitLab development environment.

Automated Code Review

Streamline merge request reviews with AI-powered insights that highlight potential issues and suggest improvements before code is merged.

CI/CD Pipeline Optimization

Leverage AI to assist in configuring, troubleshooting, and optimizing continuous integration and deployment pipelines across the software lifecycle.

Enhanced DevSecOps Workflows

Integrate intelligent automation throughout the DevOps process to boost team productivity and reduce manual tasks across planning, coding, and deployment stages.

Pros & Cons

Pros

Automates complex tasks with agentic workflows
Provides event-driven execution for reliable and repeatable automation
Offers enterprise-grade governance and control with clear permissions and transparency
Integrates external agents such as Claude Code and Codex into the GitLab workflow
Enables customizable assistance and a centralized AI catalog

Cons

Dependent on the quality of the external agents integrated into the workflow
May require significant upfront setup and configuration
Limited documentation for self-hosted models
Dependent on the quality of the GitLab Orbit lifecycle context graph

Reviews

4.3

Average from 4 ratings.

Wei Chen

May 10, 2026

Does the job

Pretty happy overall. The onboarding just works and the value for money is strong. The mobile experience lags can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.

Esther Adeyemi

Apr 29, 2026

Years in this space

I've evaluated a lot of these over the years. What stands out here is the API — handled better than most — and the value for money is strong. A few rough edges remain is my one real gripe. Worth the time if this is your use case.

Aisha Khan

Dec 17, 2025

Does the job

Pretty happy overall. The dashboard just works and support is responsive. The docs could be deeper can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.

Devin Walker

Oct 1, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on the automation, and the value for money is strong caught me off guard. The mobile experience lags is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Q&A

What are agents and flows?

Agents are orchestrated by software team members to automate tasks in the software development lifecycle. Flows are configured to automate complex tasks across multiple stages of the SDLC by taking a series of actions with agentic AI.

Asked by Olamide Fashola · Nov 27, 2025

Will my code be used for training AI models?

GitLab does not train generative AI models based on private (non-public) data. The vendors we work with also do not train models based on private data. Learn more here.

Asked by Vincenzo Greco · Nov 10, 2025

Is GitLab Duo Agent Platform open core?

Yes. GitLab has an open core business model that enables us to build with our customers, who can contribute new capabilities to our product.

Asked by Ximena Torres · Nov 7, 2025

How can I use outputs generated by GitLab Duo Agent Platform?

Output generated by GitLab Duo can be used at your discretion and, if a third-party claim arises from your use of the output generated by GitLab Duo, GitLab will step in and defend you.

Asked by Ekaterina Orlova · Oct 8, 2025

How is GitLab Duo protecting customer data?

You can read about GitLab Duo data usage here. You can also learn more about how GitLab is implementing governance and transparency in GitLab Duo via our AI Transparency Center.

Asked by Marcus Bell · Oct 8, 2025