Google has introduced Project IDX, a browser-based development environment that combines templates and generative AI assistance to make it easier to build and deploy full-stack and multiplatform applications with popular languages and frameworks. Would-be users of the preview service must start by joining a waitlist.
Built on Google Cloud and powered by the Codey foundational AI model, Project IDX starts with a web-based workspace that will feel familiar to developers, Google said. Google with Project IDX is exploring how innovations in AI including Codey and the PaLM 2 large language model can help developers write higher quality code and build applications faster.
Codey provides smart code completion, an assistive chatbot, and contextual code actions such as “add comments” and “explain this code.” AI capabilities for the project are in an early phase, Google said. Code OSS, Microsoft’s GitHub repository for developing the company’s Visual Studio Code editor, also is used by Project IDX.
Introduced August 8, Project IDX is intended to address the difficulty of developing full-stack, multiplatform apps, Google said, in which developers must navigate an “endless sea of complexity, duct-taping together a tech stack that’ll help you bootstrap, compile, test, deploy, and monitor your apps.”
Each Project IDX workspace has the full capabilities of a Linux-based VM, paired with universal access provided by the cloud. New projects can be created from templates for popular frameworks including Angular, Flutter, Next.js, React, Svelte, and Vue, while existing projects can be imported from GitHub. Backing for Python, Go, and other languages will arrive soon, joining support for JavaScript and Dart, Google said.
A fully configured Android emulator and an embedded iOS simulator are also due to arrive shortly, joining a built-in web preview already available. Firebase Hosting also enables shareable previews of web apps before deployment to production. Future plans call for more collaboration capabilities, deeper framework integrations, and more personalized and contextual AI assistance.