Copyright 9to5Mac
Today, Anthropic rolled out Claude Code on the web and iOS, launching it as a research preview to subscribers on its Pro and Max plans. Here’s what that means. Over the past year, most developers who have been using LLMs as part of their coding workflow have agreed that Claude is among the best LLMs out there for the task. Building on that, Anthropic release Claude Code earlier this year, which is basically a command-line tool that lets developers delegate coding tasks to Claude directly in their terminal. With today’s update, Anthropic is now extending Claude Code to the web, letting developers “run multiple tasks in parallel across different repositories from a single interface”. Here’s Anthropic on today’s press release: Claude Code on the web lets you kick off coding sessions without opening your terminal. Connect your GitHub repositories, describe what you need, and Claude handles the implementation. Each session runs in its own isolated environment with real-time progress tracking, and you can actively steer Claude to adjust course as it’s working through tasks. Here’s a demo of Claude Code running on the web: The company says that the web-based Claude Code version is ideal for running well-defined tasks, such as bug fixes or other routine updates. Still, it can also handle tasks such as backend changes, and answering questions about how repositories are organized. When it comes to security, Anthropic goes to great lengths to explain the technical aspects of the sandbox structure it employs, and you can find that documentation here and here. As for the iOS app, Anthropic notes that, like the web-based version of Claude Code, it is an early research preview, so the company hopes “to quickly refine the mobile experience based on” developers feedback. But in essence, it will offer a quick way for developers to review code, run small tasks, or check the progress on ongoing coding sessions. Have you been using Claude Code? Let us know in the comments. Accessory deals on Amazon
