Blog Engineering GitLab and Tabnine: AI-powered code completion for GitLab repositories
Published on March 2, 2022
3 min read

GitLab and Tabnine: AI-powered code completion for GitLab repositories

Development teams can get a custom AI model based on their private code that enables knowledge sharing, reduced technical debt, and more.


As AI continues to become more ubiquitous throughout every aspect of our lives, it should come as little surprise that programming has picked it up as a tool to help make developers more productive. Tabnine is integrating with GitLab to bring Tabnine's AI-powered code completion technology to GitLab repositories to improve the accuracy and speed of code development.

We believe that increased development velocity improves the developer’s working experience, accelerates feature release cadence, and enables teams to respond faster to market opportunities. Users can now get a custom AI model based on their private code that enables:

  • Knowledge sharing
  • Reduced technical debt
  • Faster code reviews
  • Faster onboarding and time to value

The value of a custom model is about helping a specific team with a specific mission be more productive. A team comes in many forms from the most simple two pizza box team to a large software company with hundreds of internal developers as well as thousands of external developers who contribute to a large shared open source code base. What all these teams have in common is that they have a shared interest in a common code base. This code base for any digital company is one of the most important strategic assets and anything that helps them build it faster and more consistently requires serious consideration.

GitLab has a robust platform for hosting code for private teams, so it is natural that we wanted to make it easier for teams to bring their development models together. Developers can now automate the creation of a custom model based on their private code. The process is outlined below and is seamless for the user as Tabnine will build, validate, and upload the private model for the whole team. New developers can now be added to the team and will immediately receive custom suggestions based on the codified best practices of the team.

This is the first of ongoing work that Tabnine is doing to support developers together with GitLab and we look forward to getting your feedback on how we can make it better for you individually and for your team.

Here's how to get started:

  1. As a Tabnine for Teams user, login to AI Code Completions for Developers & Teams
  2. Navigate to the “Team AI” tab
  3. Connect to your GitLab repositories
  4. Tabnine will build, test, and upload your private team model
  5. Enjoy your personalized Tabnine AI assistant

Getting started

The GitLab partnership represents Tabnine's latest step towards the goal of an end-to-end development platform supporting all developers regardless of working environments, coding languages, or IDEs. Share your feedback with Tabnine on our AI-powered code completion technology.

We want to hear from you

Enjoyed reading this blog post or have questions or feedback? Share your thoughts by creating a new topic in the GitLab community forum. Share your feedback

Ready to get started?

See what your team could do with a unified DevSecOps Platform.

Get free trial

New to GitLab and not sure where to start?

Get started guide

Learn about what GitLab can do for your team

Talk to an expert