Anthropic adds Agent View to Claude Code CLI interface

Anthropic is rolling out Agent View for Claude Code, a new Research Preview that turns parallel coding sessions into a single command-line control center. Instead of keeping several terminal tabs, tmux panes, or separate Claude Code runs open, developers can now open one screen, launch agents, send sessions into the background, check which tasks are running, see which ones need input, and jump back into a full session only when needed.

The feature is aimed at developers and teams already using Claude Code for multi-step software work. It is available now for Pro, Max, Team, Enterprise, and Claude API plans, with normal rate limits still applying. Users can opt in from the terminal by running claude agents. The feature requires Claude Code v2.1.139 or later, and administrators can disable it for an organization through managed settings.

Agent View works as a session roster inside the CLI. Each row shows a Claude Code session, its current state, its last activity, and whether it is working, waiting for input, completed, failed, idle, or stopped. Developers can open it from any session with the left arrow or start it directly with claude agents. They can also move an existing session into the background with /bg, launch a new background job with claude --bg "", peek at the latest turn with the spacebar, reply inline, or attach to the full transcript with Enter or the right arrow.

For Anthropic, this release fits its broader push to make Claude Code less like a chat-driven coding tool and more like an agent operations layer for software teams. The company has already been building around subagents, agent teams, skills, hooks, Remote Control, scheduled prompts, and Claude Code on the web. Agent View now gives those workflows a visible command center, making it easier for developers to dispatch bug fixes, PR reviews, test runs, dashboard updates, and longer-running coding jobs without losing track of where each agent stands.

Source