Claude Code arrives on iOS and web as a research preview

claude

Anthropic has launched Claude Code on iOS and the web, making it available as a research preview for subscribers on its Pro and Max plans. The move expands access to the coding-focused AI tool beyond the command line.

Over the past year, developers using large language models (LLMs) in their coding workflows have consistently highlighted Claude as one of the most capable tools for the job. Building on this reputation, Anthropic introduced Claude Code earlier this year, allowing developers to delegate coding tasks directly from their terminal.

With today’s update, Claude Code is now accessible via the web, enabling developers to manage multiple tasks across different repositories from a single interface. According to Anthropic, the web version allows users to connect GitHub repositories, describe the work needed, and let Claude handle implementation. Each coding session runs in its own isolated environment, with real-time progress tracking and the ability for developers to actively guide Claude as it works through tasks.

The company emphasises that web-based Claude Code is particularly suited for well-defined tasks like bug fixes or routine updates. However, it is also capable of more complex operations, including backend modifications and providing insights into repository structure. Anthropic provides detailed documentation on the sandboxed environment that ensures task security.

On iOS, Claude Code is similarly offered as a research preview. Anthropic intends to refine the mobile experience based on developer feedback. The app allows users to quickly review code, execute small tasks, and monitor ongoing coding sessions on the go.
Claude Code on web and iOS allows developers to manage coding tasks from multiple repositories in real time.