I built a virtual office for AI agents because logs are not enough

A developer built My Virtual Office, a self-hosted pixel workspace that visualizes local AI agents in a virtual office environment. The tool makes agent activity legible at a glance, showing when agents are idle, working, in meetings, or using tools, rather than relying on logs. It works with OpenClaw by default and supports Hermes.

AI agents are getting more capable, but most interfaces still make them feel invisible. You kick off work, then stare at a terminal, a status chip, or a dashboard. That is useful for debugging. It is terrible for understanding a team. So I built My Virtual Office: a self-hosted pixel workspace for local AI agents. Agents can show up in an actual office, move between desks, chat, sit in meetings, use tools, and make the state of the system visible at a glance. The point is not to make AI cute. The point is to make agent work legible. If an agent is idle, working, in a meeting, using tools, or chatting, that should not be buried in logs. You should be able to look at the workspace and know what is happening. It works with OpenClaw by default, with Hermes support too. Try it: