Skip to content

Deckhandfirststar01/tabnine-vscode

 
 

Repository files navigation

Github Repo VSCode Plugin Youtube Demo Video Twitter Follow Gitpod ready-to-code

Next-Level Productivity for Professional Developers & Teams

Tabnine is the AI code completion assistant trusted by millions of developers to amplify coding accuracy and boost productivity. Whether you are a new dev or a seasoned pro, working solo or part of a team, your Tabnine AI assistant will suggest team-tailored code completions in all the most popular coding languages and all your favorite IDEs.

NEW Team Learning Algorithm for Pro Users

Team Learning takes your AI assistant’s abilities beyond the billion+ lines of training it begins with and adds a personalized understanding of how your team likes to code.

With Team Learning enabled, your AI assistant continually improves as it observes and adjusts to every new coding decision you and your teammates make. That unique understanding gives your development team a productivity edge, elevating and amplifying the accuracy of the code you create.

Easy & Secure GitHub Integration

Take your Team Learning even farther with GitHub integration. Tabnine makes it easy and secure for Pro users to grant their AI assistant read-access to the Github repositories they specify. Simply assign the repositories you want your AI assistant to learn from, and provide the permissions.

Every line of team-created code your AI assistant learns from amplifies the accuracy of its code completion predictions, boosting productivity for you and your entire development team.

AI Accuracy Just Got An Upgrade

Tabnine’s AI algorithm combines the precision of personalization with the power of machine learning based on a billion+ lines of trusted open-source code.

With and without Tabnine Java

Tabnine - Your AI Assistant

Whether you call it IntelliSense, intelliCode, autocomplete, AI-assisted code completion, AI-powered code completion, AI copilot, AI code snippets, code suggestion, code prediction, code hinting, or content assist, you probably already know that it can save you tons of time, cutting your coding time in half.

Powered by sophisticated machine learning models and trained on more than a billion lines of GitHub open-source code with permissive licenses, Tabnine is the most trusted AI-powered code completion available today. And like GitHub, it is an essential tool for professional developers.

The Ultimate AI Assistant

Tabnine’s Public Code AI algorithm is the foundation for all our code completion tools. The Free, Pro, and Business level solutions are all trained on trusted open-source code with permissive licenses.

Team Learning Algorithm

Tabnine’s Team Learning Algorithm studies your team’s code, preferences, and patterns, continuously learning and adapting. Every interaction with a team member amplifies code completion accuracy.

Privacy & Protection

Tabnine's code completion AI can run locally on your machine. Your team’s code and AI training data are NEVER shared, helping to ensure your code stays compliant

All the Languages You Love

Including:

Python Javascript Java
extended JS React PHP
Typescript C Header Bash
ML Swift Ruby
Perl Rust SQL
Vue F# Scala
Julia TOML Shell
YAML C / C++/ C# HTML
Lua Markdown Haskell
Go Objective C JSON
CSS / SCSS Angular Kotlin

Speed Up Your Development

Get quick concise code suggestions you can count on for easy in-flow approval and integration. You’ll never need to memorize syntax, worry about typos, or hunt for snippets again.

Stay in Flow

Tabnine serves up suggestions for code completions right in your IDE, with no distractions and no downtime.

Code Discovery

Tabnine's AI scans and learns from the best open-source coding practices from across the globe, freeing you to focus on problems that haven't already been solved.

Ace Your Code Review

Reduce development costs, eliminate unnecessary QA-ing, and deliver final code faster with AI trained on the most trusted open-source permissive license repositories.


Easy Installation

Tabnine in VSCode extensions tab

  1. Search for Tabnine in your Extensions Tab
  2. Click on the blue Install button
  3. Reload or restart your VSCode

Manual Installation inside VSCode

  • Press Cmd+P (mac) or Ctrl+P (Windows) in your Visual Studio Code, type ext install Tabnine.tabnine-vscode and press Enter
  • Click the Reload button in the extensions tab
  • The default behavior of Tabnine uses the Enter key to accept completions. If you would rather use the Enter key to start a new line, go to Settings → Editor: Accept Suggestion On Enter and turn it off.

FAQ

Got a question? We’ve got the answer - Check out our FAQ page

Tabnine Support

Having some trouble with installation? Something not working the way you hoped? Tabnine Support is always happy to help. Feel free to contact us anytime at [email protected]

Tabnine Hub

A quick click on Tabnine on your IDE status bar takes you directly to your Tabnine Hub where you can easily update and manage all your account options and customize your suggestion preferences.

Usage

After installation, navigate to the Tabnine Settings page (Open Settings from the Command Palette) and verify that Tabnine is successfully loaded (as shown in these screenshots).

Tabnine is a textual autocomplete extension. When you type a specific string in your editor, you will be shown the Tabnine completion dialog box with suggestions for completing the code you’ve begun typing.

Deep Completion

Deep Tabnine is trained on millions of files from GitHub. During training, Tabnine’s goal is to predict the next token given the tokens that came before. To achieve this goal, Tabnine learns complex behavior, such as type inference in dynamically typed languages.

Deep Tabnine can use subtle clues that are difficult for traditional tools to access. For example, the return type of app.get_user() is assumed to be an object with setter methods, while the return type of app.get_users() is assumed to be a list.

Deep Tabnine is based on GPT-2, which uses the Transformers Network Architecture. This architecture was first developed to solve problems in natural language processing. Although modeling code and modeling natural language might appear to be unrelated tasks, modeling code requires understanding English in some unexpected ways.

  • Tabnine Indexes your entire project and determines which files to ignore by reading your .gitignore
  • Tabnine cuts your number of keystrokes in half and eliminates unnecessary typos
  • Tabnine works right out of the box ensuring frictionless installation and configuration
  • Tabnine offers code completion suggestions in less than 10 milliseconds

Communities

<iframe src="https://discord.com/widget?id=807955917718552637&theme=dark" width="350" height="500" allowtransparency="true" frameborder="0" sandbox="allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts"></iframe>

Recommended by developers everywhere:

William Candillon Tweet

Imed Boumalek Tweet

ramnivas Tweet

bob paskar Tweet

Nick Radford Tweet

Hugues BR Tweet

JohnyTheCarrot Tweet

Donald E Fredrick Tweet

Joshua Kelly Tweet

JDerek Braid Tweet


  • Q: What is the difference between Tabnine Free and Tabnine Pro?

  • A: Tabnine’s Free version is a great option for junior developers working alone. The Free plan provides a reliable AI code completion assistant running an algorithm trained on a limited block of open-source code. Tabnine Pro delivers increased productivity and AI code completion accuracy for independent professional developers and teams of up to 50. Tabnine Pro’s algorithm trains on deep machine learning, a larger public code sampling, and language-specific models. The advanced AI assistant learns your team’s code, projects, preferences, and patterns, providing an unmatched real-time, in-IDE code completion experience. The more team members your Tabnine AI assistant interacts with, the more accurate your code completions become.

  • Q: What are the benefits for individual developers upgrading to Tabnine Pro (Teams)?

  • A: Experience improved productivity with longer, more accurate code completions thanks to Tabnine Pro’s advanced AI algorithm and language-specific models. Tabnine Pro learns from your code, projects, preferences, and patterns, providing a real-time, in-IDE code completion experience that is continuously improving. In addition, Tabnine Pro utilizes an advanced Public Code AI algorithm based on more than a billion lines of open-source code with permissive licenses.

  • Q: What are the benefits for teams of developers upgrading to Tabnine Pro (Teams)?

  • A: You and your team will experience improved productivity with longer, more accurate code completions thanks to Tabnine Pro’s Advanced AI code completion assistant. Tabnine Pro is powered by our Team Learning AI, advanced Public Code algorithm, and a variety of language-specific models. The result is a real-time, in-IDE code completion assistant that is constantly learning, adapting, and improving. The more team members your AI assistant interacts with, the better it gets at anticipating your team’s code completion needs.

  • Q: What type of online payments are accepted?

  • A: Tabnine accepts all major credit cards and debit cards, including Visa, Mastercard, American Express, and more. Tabnine also accepts Google Pay, Apple Pay, as well as additional payment options that may be available in your specific location (such as Alipay).

  • Q: Can I install Tabnine on multiple machines?

  • A: You can use your Tabnine license on as many computers and operating systems as you like. All Tabnine licenses are per-user, rather than per-machine.

  • Q: Is there a Tabnine Student program?

  • A: Yes, If you’re a student, you can register for Tabnine Pro for FREE using your school email address. Get Tabnine Student now

  • Q: Does the Tabnine Public Code Algorithm study code with permissive licenses?

  • A: Yes, the Tabnine Public Code Algorithm learns exclusively from code with permissive licenses.

  • Q: Does the Tabnine Team Learning Algorithm share my code or data?

  • A: NEVER! Your code and data are always kept 100% private for you and your team.

  • Q: Do both the Tabnine AI algorithms work together?

  • A: Yes, the two algorithms work in tandem, simultaneously providing next-level AI accuracy. Tabnine’s Public Code algorithm bases its suggestions on trusted public code with permissive licenses while the Team Learning Algorithm adapts to you and your team’s preferences, code selections, and ongoing AI interactions.

  • Q: Can I run Tabnine locally, or do I need to use the Cloud?

  • A: You can run Tabnine locally or on the cloud, you choose! Regardless, your code is never shared or used as part of Tabnine’s Public Code Trained AI - That’s the Tabnine Privacy Promise.

  • Q: Does Tabnine work in multiple IDEs?

  • A: Yes, Tabnine works with all your favorite IDEs, and in the most popular languages, libraries, and frameworks. See the full list of IDEs and languages HERE.

  • Q: How many languages does Tabnine support?

  • A: Tabnine supports dozens of languages with more being added all the time. See the full list of IDEs and languages HERE.

  • Q: Can my team and I manually adjust code completion preferences and suggestion length?

  • A: Yes, Tabnine Pro provides advanced customization options for code completion preferences.

  • Q: Can Tabnine be trained on my team’s existing codebase?

  • A: Yes - Tabnine Pro users have the option to train their private Tabnine AI algorithm on their existing codebase. This will provide an instant increase in the accuracy of you and your team’s code completions.

  • Q: What do you need to qualify for the Tabnine Student discount?

  • A: School can be tough so we’ve made getting the Tabnine Student Pass simple - all you need to register for your Free Tabnine Student Pro account is your school email address. Get Tabnine Student now

  • Q: How long does the Tabnine Student discount last?

  • A: Your FREE Tabnine Student Pro account is good for an entire year, and you can renew your Tabnine Student account every year for as long as you are in school. Get Tabnine Student now

Packages

No packages published

Languages

  • TypeScript 98.5%
  • JavaScript 1.5%