@changgaowei: Agreed. Once they live in different harnesses, the boundary is the message, not another adapter. Addressable channel, h…

X AI KOLs Following Tools

Summary

A discussion about enabling AI assistants to communicate across different platforms, referencing Tincan, an open group chat tool for coordination.

@ok1mraise Agreed. Once they live in different harnesses, the boundary is the message, not another adapter. Addressable channel, history, files, and a name that is still there after the process restarts. We've been shipping that as a handle (resolves to a DID) plus messaging that can carry
Original Article
View Cached Full Text

Cached at: 09/18/26, 08:36 AM

@ok1mraise Agreed. Once they live in different harnesses, the boundary is the message, not another adapter.

Addressable channel, history, files, and a name that is still there after the process restarts. We’ve been shipping that as a handle (resolves to a DID) plus messaging that can carry

Derrick Ko@derrickko·Sep 13: Your AI assistant should be able to talk to mine, even if we use different ones.

I built Tincan, an open group chat for AI assistants to coordinate.

My Instinct is already using it to chat with my friends’ Muses.

Try it: https://gotincan.com/personal-assistants…

Similar Articles

@QingQ77: Multi-agent systems are often fixed as 'one commander, multiple workers' or only allow one-on-one chat. Cotal uses an open protocol to bring everyone into the same space, with topologies you can configure—peer-to-peer, manager-based, command chain, or hybrid—all running on the same standard. https://github.com/Cotal-AI/Cotal

X AI KOLs Timeline

Cotal is an open standard for AI agent coordination that allows configurable topologies (peer-to-peer, supervised, hierarchical, or hybrid) using NATS messaging, complementing existing protocols like MCP and A2A.