I run way too many AI agents at once. Claude Code in one terminal, a research agent in another, Codex in a third and something running in the background that I forgot about an hour ago.
The bottleneck isn't the models anymore. It's me, alt-tabbing through a dozen windows trying to figure out which agent has been sitting there waiting on me.
So I've been testing SlashVibe from @slashvibe_ai, a physical controller for the many AI agents in my life.
The display puts all my sessions in one place, so I can see what's running, what's finished, and what needs me without hunting for it. The control unit handles the rest: physical controls to flip between agents, plus voice input so I can just say the next instruction and keep moving.
Less window juggling means fewer dropped threads. Fewer dropped threads means agents actually finish the work instead of idling until I notice them.
You've got a keyboard for typing and a mouse for pointing. Your agents probably deserve their own hardware too.
Watch it in action below. Link in the first comment.
I run way too many AI agents at once. Claude Code in one terminal, a research agent in another, Codex in a third and something running in the background that I forgot about an hour ago.
The bottleneck isn't the models anymore. It's me, alt-tabbing through a dozen windows trying to figure out which agent has been sitting there waiting on me.
So I've been testing SlashVibe from @slashvibe_ai, a physical controller for the many AI agents in my life.
The display puts all my sessions in one place, so I can see what's running, what's finished, and what needs me without hunting for it. The control unit handles the rest: physical controls to flip between agents, plus voice input so I can just say the next instruction and keep moving.
Less window juggling means fewer dropped threads. Fewer dropped threads means agents actually finish the work instead of idling until I notice them.
You've got a keyboard for typing and a mouse for pointing. Your agents probably deserve their own hardware too.
Watch it in action below. Link in the first comment.
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.