Anthropic has launched a research preview of Claude Code for the web and iOS, now available to its Pro and Max plan subscribers. The update extends an existing command-line tool, enabling developers to delegate coding tasks through new graphical interfaces.
This release follows a period over the past year in which developers using large language models for coding have rated Claude as one of the leading options for such tasks. Building on this developer feedback, Anthropic first released Claude Code earlier this year as a command-line utility. This initial version gave programmers the ability to assign coding work directly to the AI from their terminal.
The new web-based version expands this functionality, allowing developers to initiate coding sessions without a terminal. According to Anthropic, “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 operates in an isolated environment with real-time progress tracking, and users can actively steer the AI to adjust its course while it works.
The web interface supports running multiple tasks in parallel across different repositories from a single dashboard. Anthropic notes the web version is best suited for well-defined assignments, such as bug fixes or routine updates. It can also manage more involved work, including backend changes, and can answer questions about the structure of a repository. For security, Anthropic provides detailed technical documentation that outlines the sandbox architecture it employs for these coding sessions.
The accompanying iOS app is also an early research preview. It is designed to offer a quick way for developers to review code, run small tasks, or check the progress of ongoing coding sessions from a mobile device. Anthropic stated it plans to use feedback gathered during the preview to refine the mobile experience.