Anthropic Launches Claude Code on the Web, Lets Users Assign Parallel Coding Tasks

Anthropic is finally expanding the accessibility of its Claude Code product. The artificial intelligence (AI) tool, which was so far available as a command-line interface (CLI) on compatible desktops, can now be accessed via a web app. The web version of the coding tool is currently available as a research preview to the paid subscribers, and it brings several improvements over the coding interface of Claude chatbot. The tool can perform multiple coding tasks in parallel and connect to GitHub repositories.

Claude Code Is Now Available on the Web

In a newsroom post on Monday, the San Franciso-based AI firm announced the expansion of Claude Code to web. With this, eligible users will no longer need to download the CLI to access the sandboxed coding tool. Instead, the AI system can be given tasks right from the browser, as long as it is connected to the user's GitHub repo. Currently, it is available in beta as a research preview, and those interested in trying it out will require a Claude Pro or Max subscription.

Claude Code on the web also brings the AI system from inside the user's terminal to the cloud. There is a trade-off in security and privacy, but those users who are willing to let that go will now get new features due to the extra processing power from the cloud servers. Among them is the ability to run multiple coding tasks in parallel. These tasks can be across different repositories, all manageable via a single interface, and every completed task comes with a pull request (PR) button and change summaries.

Additionally, each coding session runs in its own isolated environment where the user can monitor real-time progress. Users can also prompt Claude Code to focus on specific elements and add subtasks while it is actively coding. Anthropic says the AI tool excels in bug fixes, tasks that are well-defined, and making backend changes.

Anthropic has also made Claude Code available on smartphones. Currently, the coding tool can be accessed via the Claude for iOS app. However, the company highlights that it is an early preview, and it will refine the mobile experience based on user feedback.

While running Claude Code via cloud comes with more security risks than running it from the terminal, the company claims that it has taken measures to ensure that user data remains secure. Each coding task is kept in an isolated environment with network and filesystem restrictions.

Additional GitHub interactions are handled via a proxy service to ensure that the AI can only access authorised repositories. Users and admins also have control over choosing the domains Claude Code can connect to via custom network configuration.