Anthropic has introduced Agent View for Claude Code, a new Research Preview feature that gives developers a centralized way to manage multiple coding agents running in parallel from the command line. The feature, available now for Pro, Max, Team, Enterprise, and Claude API users, turns Claude Code sessions into a unified control panel where developers can launch agents, move tasks into the background, monitor progress, and respond only when a session requires input.
The release is aimed at developers already using Claude Code for longer-running software tasks that often involve juggling several terminal windows, tmux panes, or independent coding sessions at once. Anthropic says Agent View lets users open a single interface showing which sessions are active, waiting for feedback, completed, failed, idle, or stopped.
Developers can launch the interface with the claude agents command or open it from an existing session using the left arrow key. Each session row displays the latest activity, the most recent response, and whether the agent is still working or needs attention. Users can preview the latest exchange without fully attaching to the session, respond inline if the agent is waiting on a decision, or reopen the full transcript when deeper interaction is needed.
Anthropic is also expanding background execution workflows inside Claude Code. Existing sessions can be moved into Agent View with the /bg command, while entirely new background jobs can be started directly from the terminal using claude –bg . The company says this is intended to help developers manage bug fixes, pull request reviews, dashboard updates, and other extended coding tasks without continuously monitoring each process.
The launch reflects Anthropic’s broader push to position Claude Code as more than a conversational coding assistant. Over recent months, the company has added features tied to subagents, skills, hooks, scheduled prompts, Remote Control functionality, and web access for Claude Code. Agent View appears designed to unify those workflows into a more operational interface for teams running multiple AI-assisted development tasks simultaneously.
Anthropic says the feature is currently available as a Research Preview and requires Claude Code version 2.1.139 or later. Enterprise administrators can disable the functionality through managed settings, while standard usage rate limits still apply.
About this article: This article was generated with AI assistance and reviewed by our editorial team to ensure it follows our editorial standards for accuracy and independence. We maintain strict fact-checking protocols and cite all sources.
Word count: 390Reading time: 0 minutes
Explore More AI Resources
Continue with high-value guides related to this topic.
