Codex's Agents Dashboard turns a pile of terminal tabs into one queue
OpenAI's Codex CLI has quietly grown the missing management layer for people who run several coding agents at once — an Agents Dashboard that groups every active session by project and state, plus a companion command that lets you message any session without opening it. A hands-on from developer and AI researcher Vladislav Guzey walks through the workflow, and it reads less like a feature tour than a small thesis about where developer tools are heading: when the work is automated but supervising the work isn't, the interface that wins is the one that answers "where is my attention needed?"
The dashboard's core move is triage. Sessions sort into states — blocked on you, working, ready for review — which replaces the old habit of scanning terminal tabs for whichever output changed most recently. The deeper fix is decoupling communication from navigation: a second terminal command accepts a task name or session ID plus a message (and even image attachments for visual bugs), so a script or a colleague can add context to a running agent mid-flight without taking over its screen. Guzey's honest caveat is worth keeping: none of this makes parallel work free — more agents still mean more decisions to make and more output to review. What it removes is pure navigation cost.
Our take: this is the same "agents need an operating layer" shift we've tracked across the ecosystem — we mapped the trend when agent tooling went desktop-native — but it hits differently coming from inside a mainstream coding agent rather than the open-source harness scene. When the primary interface becomes a queue of tasks competing for your attention instead of one conversation, the developer's job description quietly changes from writer of code to reviewer of queues. GitHub's issue tracker shows real usage forming around both features — including requests to extend the dashboard itself.
What to watch: whether Anthropic and Google's coding CLIs copy the state-triage model within weeks, and whether "agent fleet dashboards" become a standard job category in dev tools the way CI dashboards did.
Running three coding agents before lunch? Tell us in the comments whether a queue view would change how you supervise them.
Sources: openai/codex on GitHub
