If you have been running multiple Claude Code sessions in parallel — different tabs, tmux panes, split terminals — you already know the chaos that comes with it. Anthropic has introduced Agent View, a new feature for Claude Code designed for centralised management of multiple AI agent sessions simultaneously. It launched on May 11, 2026 as a Research Preview, and it is the most practical quality-of-life upgrade Claude Code has shipped this year.

What Is Agent View?

Agent View is a CLI dashboard that puts every Claude Code session on one screen, replacing tmux juggling. Run claude agents from the shell, or press the left arrow inside any session, and a roster appears. Each row shows what a session is doing, whether it is blocked on your input, and the contents of its last response.

Each row shows the session, whether it needs your input, the contents of its last response, and when you last interacted with it. Select a session to peek at the last turn. If a session is waiting on a decision, answer inline and the session picks back up. Press Enter to attach directly to sessions where you want to explore the full transcript.

One dashboard. Every agent. No context switching.

How to Use It

Getting into Agent View requires Claude Code v2.1.139 or later. Check your version and update if needed, then:

Action	Command
Open Agent View	`claude agents` in terminal
Open from active session	Press left arrow
Send session to background	`/bg` slash command
Launch fresh background session	`claude --bg [task]`
Peek at last response	Spacebar
Attach to full session	Enter

Users can also view an agent’s most recent messages without opening the full session, and can intervene only when the system requires confirmation or input.

Why This Matters for Developers

Most developers running Claude Code in 2026 are juggling between three and eight parallel sessions at once — different bug fixes, PR reviews, refactors, and feature builds all running simultaneously. Until now, managing that meant either terminal tab chaos or setting up tmux grids manually. Agent View absorbs that coordination cost into the tool itself.

The goal is letting developers dispatch several ideas at once, each optionally paired with a skill, and return to a list of pull requests ready for review. That workflow — send five agents off on five parallel tasks, do other work, come back and review outcomes — is exactly how elite engineering teams at Stripe and other early Claude Code adopters have been operating. Agent View makes it accessible without the setup overhead.

Fits Into a Larger Agent Infrastructure Push

Agent View does not arrive in isolation. The same week also saw Anthropic ship Dreaming, Outcomes, and multiagent orchestration for the Claude Managed Agents platform — making this part of a coordinated push to position Claude Code as a full multi-agent development platform, not just a single AI coding assistant.

Dreaming lets agents review their own past sessions between jobs and write new memory entries the next session can use. Legal-AI startup Harvey ran the pilot and saw task completion rates climb roughly six times.

Together, Agent View on the CLI side and Dreaming plus multiagent orchestration on the Managed Agents side represent Anthropic’s most complete answer yet to the question of what serious parallel AI-assisted development actually looks like in practice.

Availability and Plans

Agent View is available as a Research Preview on Pro, Max, Team, Enterprise, and Claude API plans. Organisation admins can switch it off with a disableAgentView managed setting, and keyboard shortcuts may change as the preview evolves.

For developers who are also exploring Claude Code for VS Code or the Claude Code JetBrains plugin, Agent View is CLI-native for now — the multi-session sidebar in the desktop app handles the equivalent experience in the GUI.

The Bottom Line

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. Agent View is the command centre that makes that vision legible to a single developer sitting at a terminal. If you are already running parallel Claude Code sessions, update to v2.1.139 and run claude agents today.

Stay tuned to TechnoSports for the latest developer tools, AI coding updates, and Claude Code news.