GitLab Code Suggestions is an AI-assisted tool designed to enhance coding productivity while maintaining the security of proprietary source code. It leverages billions of lines of code to provide predictive code completions, function logic definitions, test generation, and common code proposals like regex patterns, all within the user's existing coding environment. Emphasizing privacy, it ensures that private, non-public customer code stored in GitLab is not used for training data.
The tool supports 14 programming languages, including C++, Java, Python, and TypeScript, and integrates seamlessly with popular IDEs such as GitLab Web IDE, VS Code, Visual Studio, Jetbrains-based IDEs, and NeoVIM. GitLab Code Suggestions is also available for self-managed GitLab instances via a secure connection to GitLab.com.
Continuous improvements are being made to enhance suggestion quality through advanced prompt engineering, intelligent model routing, and expanded context windows. This tool is part of GitLab's broader AI-powered DevSecOps platform, aimed at accelerating software development without compromising security.
Information shown may be outdated. Found an error? Report it here
