Serdar Yegulalp
Senior Writer

Kite brings its AI-powered code completion to JavaScript

news
May 13, 20202 mins

Originally for Python only, Kite has added a JavaScript-trained machine learning model to its add-on for popular code editors and IDEs

artificially intelligent, robotic workers
Credit: Thinkstock

Kite, maker of an AI-powered auto-complete programming tool for Python, has added JavaScript support. The company also introduced a pro-grade paid plan to supplement its free add-on for Visual Studio Code, Sublime Text, Atom, and other popular editors and IDEs.

Kite uses machine learning powered models, created from millions of lines of open source Python and JavaScript code, respectively, to make code-completion predictions as you type. Its predictions are derived from abstract syntactual analysis of the code, not just static code listings, and its suggestions are contextual, based on the code that both you and other programmers have written in similar situations.

Kite was originally offered for Python, with plans to expand support to other languages—JavaScript being among the first. Kite uses data sets of behavior gathered from many popular JavaScript packages including commonly used frameworks like React, Vue, Angular, and Node.js.

Plug-in integration is avialable for most every major development environment including Visual Studio Code and Atom. The product installs locally and does not need a cloud connection to work; all predictions are served and made on one’s own system.

By default, Kite is free for both commercial and personal use. A newly launched paid product, Kite Pro, adds a few new features. The largest is single-line and multiple-line completions (for Python, right now) generated by deep learning, including data in dictionaries, import aliases, and code snippets. Price is $16.60 per month per user, billed annually. Pricing is available for teams on request.

Serdar Yegulalp

Serdar Yegulalp is a senior writer at InfoWorld. A veteran technology journalist, Serdar has been writing about computers, operating systems, databases, programming, and other information technology topics for 30 years. Before joining InfoWorld in 2013, Serdar wrote for Windows Magazine, InformationWeek, Byte, and a slew of other publications. At InfoWorld, Serdar has covered software development, devops, containerization, machine learning, and artificial intelligence, winning several B2B journalism awards including a 2024 Neal Award and a 2025 Azbee Award for best instructional content and best how-to article, respectively. He currently focuses on software development tools and technologies and major programming languages including Python, Rust, Go, Zig, and Wasm. Tune into his weekly Dev with Serdar videos for programming tips and techniques and close looks at programming libraries and tools.

More from this author