GitLab’s AI-assisted Code Suggestions

(beta)

GitLab’s AI-assisted Code Suggestions

Accelerate coding

With the help of generative AI that suggests code while you're developing, we help teams create software faster and more efficiently. Complete an entire line of code with a single keystroke, quickly start a function, fill in boilerplate code, generate tests, and more.

languages = {
    'en': {
     'hello': 'Hello',
     'goodbye': 'Goodbye'
   },
   'es': {
     'hello': 'Hola',
     'goodbye': 'Adiós'
   }
 }

code suggestion

Keep your Source Code protected

Code Suggestions is built with privacy as a critical foundation. It keeps your proprietary source code secure within GitLab's enterprise cloud infrastructure. Your code is not used as training data. Source code inference against the Code Suggestions model is not retained. Learn about data usage when using Code Suggestions.

/nuxt-images/solutions/code-suggestions/secure-code.svg

Billions of lines of code at your fingertips

Code Suggestions uses open-source pre-trained models that are continuously fine-tuned with a customized open-source dataset to enable multi-language support and additional use cases.

languages = {
    'en': {
     'hello': 'Hello',
     'goodbye': 'Goodbye'
   },
   'es': {
     'hello': 'Hola',
     'goodbye': 'Adiós'
   }
 }

code suggestion

Support in your language of choice

AI-powered Code Suggestions that fit the way you work. is available in 13 languages: C/C++, C#, Go, Java, JavaScript, Python, PHP, Ruby, Rust, Scala, Kotlin, and TypeScript

What’s next for your AI pair programmer?

Code Suggestions for Self-managed Instances

Code Suggestions will soon be available to self-managed instances via a secure connection to GitLab.com. If you have unique requirements for your self-managed instances, we welcome you to express your interest in our self-managed support issue.

Improved user experience

We are working on additional IDE support, including JetBrains IntelliJ-based IDEs and Visual Studio support for code suggestions. Also, our plan is to improve the user experience for how suggestions are presented and accepted within the IDEs, giving developers more control over how the feature works.