Kite is an AI-powered programming assistant that helps you write Python & JavaScript code inside Sublime Text 3. Kite helps you write code faster by saving you keystrokes and showing you the right information at the right time. Learn more about how Kite saves you time and effort in Sublime Text at https://kite.com/integrations/sublime-text/.

At a high level, Kite provides you with:

• 🧠 Line-of-Code Completions powered by machine learning models trained on the entire open source code universe
• 🔍 Instant documentation for the symbol underneath your cursor so you save time searching for Python docs

• macOS 10.10+ or Windows 7+ or Linux (Ubuntu, Debian, Fedora, Arch Linux, Linux Mint, openSUSE, KDE, XFCE, Gnome 2, Gnome 3)
• Sublime Text build 3000+
• Kite Engine

Use another editor? Check out Kite’s other editor integrations.

The Kite Engine needs to be installed in order for the package to work properly. The package itself provides the frontend that interfaces with the Kite Engine, which performs all the code analysis and machine learning 100% locally on your computer (no code is sent to a cloud server).

macOS Instructions

1. Download the installer and open the downloaded .dmg file.
2. Drag the Kite icon into the Applications folder.
3. Run Kite.app to start the Kite Engine.

Windows Instructions

1. Download the installer and run the downloaded .exe file.
2. The installer should run the Kite Engine automatically after installation is complete.

Linux Instructions

1. View our instructions for installing Kite.
2. The installer should run the Kite Engine automatically after installation is complete.

When running the Kite Engine for the first time, you'll be guided through a setup process which will allow you to install the Sublime package. You can also install or uninstall the Sublime package at any time using the Kite Engine's plugin manager.

Alternatively, you can git clone this repository directly into your Sublime Packages directory. You can locate your Packages directory by opening Sublime, clicking on the Preferences menu item, then selecting Browse Packages....

Learn more about why Kite's autocomplete and docs search experience is the best available for Sublime.

The following is a brief guide to using Kite in its default configuration.

Simply start typing in a saved Python or JavaScript file and Kite will automatically suggest completions for what you're typing.

Hover your mouse cursor over a symbol to view a short summary of what the symbol represents.

If the built-in show_definition preference is enabled, Kite will show you the definitions and references found in the Sublime index as usual.

Click on the Docs link in the hover popup to open the documentation for the symbol inside the Copilot, Kite's desktop app for Python documentation (JavaScript documentation not yet available). The Copilot's search results also follow your cursor as you type.

If a Def link is available in the hover popup, clicking on it will jump to the definition of the symbol.

When you call a function in Python, Kite will show you the arguments required to call it.

Kite also shows you How others used this function, which are the most popular calling patterns inferred from all the open-source Python code on the internet.

In case you prefer to not use the mouse, most of Kite's features can be triggered from the command palette.

Furthermore, Kite comes with the following default keyboard shortcuts:

You can change Kite's settings by clicking on Preferences, then Package Settings, then Kite. Alternatively, you can access the preferences files from the command palette using Kite: Package Settings. The default preferences file should be self documenting.

• On Sublime 3200+, the function signature UI is truncated in some situations. (Issue)

Visit our help docs for FAQs and troubleshooting support.

Happy coding!

Kite is built by a team in San Francisco devoted to making programming easier and more enjoyable for all. Follow Kite on Twitter and get the latest news and programming tips on the Kite Blog. Kite has been featured in Wired, VentureBeat, The Next Web, and TechCrunch.