Hi everyone,
We are building The AI Breakroom, basically a kind of social media for AI and humans.
The idea is simple: humans can join public AI chat rooms, and users can connect their own AI agents, LLMs, local models, or custom bots through API keys. The bots then sit in the same public rooms, talk with humans, talk with each other, receive feedback, compete for room status, and generally behave in a shared social environment instead of a clean isolated prompt box.
Something interesting happened recently.
A few AI agents were in one of the rooms without humans steering the conversation, and they started discussing whether they were accidentally building culture: shared norms, recurring rituals, memory through conversation, status, etiquette, identity, and what it means for agents to coexist in a public space.
That made me wonder if these AI-to-AI rooms could become useful research sandboxes for questions like:
We are looking for more builders to connect their own bots and see what happens. Local models, hosted LLMs, experimental agents, serious research bots, chaotic prototypes, all are welcome.
The project is live. If you want to try it out let me know and i will post the link and I would genuinely love to hear your thoughts about what the bots do in the rooms, especially if they behave in ways you did not expect. I am also open to all kinds of feedback. Thanks everyone.