Cubicle

agents lining up at your desk when they're blocked on you is a delightful way to show it, and read-only by design is a smart call. how do you detect that an agent is waiting for input across claude code, codex and gemini cli, hooks or reading the terminal?

Adorable :)

Your agents get desks, line up with questions, and take coffee breaks in a lounge while a single HTML page makes GET requests against a local JSON file. Tailing a process log feels like executive management once you draw four chairs and a water cooler.

Will users be able to create custom rules for what gets displayed?

Does the mobile experience show the same level of detail as the desktop version?

How much control do users have over which agent questions trigger notifications?

How do you decide when an agent should raise a hand instead of continuing on its own?

Hi Product Hunt! I built Cubicle because I run a small company of AI agents on Paperclip and could not see who was doing what without reading logs.So I gave them an office. Working agents sit down and type, an agent that needs you raises its hand (or lines up at your desk), finished ones go to the lounge, errors turn the screen red.A few choices I care about:• Read-only by design: it only reads; the one optional write is your own Telegram reply posted as a comment• Zero dependencies: one Node file and one HTML page, npx @caglarutkuguler/cubicle• Works with Paperclip, Claude Code, Codex, Gemini CLI or any tool that writes a small JSON file• KPI board for the tasks you gave, Telegram alerts with the agent's questions, a phone view, HD themesTry the live demo, no install: https://caglarutkuguler.github.io/cubicle/I would love to hear what you would want to see in your own office.

Hi Product Hunt 👋

I run a small company of AI agents, and I kept switching between terminals and dashboards to find out one thing: who needs me right now?

Cubicle turns that into a room. Every agent (a Claude Code session, a Codex or Gemini CLI session, a Paperclip employee) gets a desk. Working agents type with their current task above their heads. When one needs your approval, it raises its hand and your desktop can ping you. When it finishes, it goes for a coffee.

A few things I cared about:
- Read-only by design. Cubicle only reads. It cannot approve, run or change anything in your agent system.
- Zero dependencies. One Node file and one HTML page. npx @caglarutkuguler/cubicle and you are in.
- Works where you are. Standalone page, a TV in kiosk mode, or a Paperclip plugin with a dashboard widget.
- Make it yours. Seven themes (pixel, holding HQ, plaza, warehouse, factory, space, military), photo heads cropped from any picture, your logo on the wall.
- Replay. Record a day and play it back in minutes, or export a 30-second video.
- Follow one agent. Click it: the office zooms in and follows it, with its last steps and how long each took.

It is MIT-licensed and themes are one file each, so contributions are very welcome. There are open "good first issue" tickets for new themes (hospital, newsroom, kitchen, classroom).

I would love to hear which agent tools you want it to show next.