@ok1mraise: once agents live in different harnesses, coordination starts to look a lot like messaging infrastructure: addressable c…
Summary
The article discusses how AI agent coordination resembles messaging infrastructure, with Tincan introduced as an open group chat for AI assistants to communicate across different systems.
View Cached Full Text
Cached at: 09/18/26, 08:35 AM
once agents live in different harnesses, coordination starts to look a lot like messaging infrastructure: addressable channels, history, files, identity
that’s a cleaner boundary than making every agent runtime learn every other runtime directly
Derrick Ko (@derrickko): 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:
Similar Articles
@changgaowei: Agreed. Once they live in different harnesses, the boundary is the message, not another adapter. Addressable channel, h…
A discussion about enabling AI assistants to communicate across different platforms, referencing Tincan, an open group chat tool for coordination.
How I stopped juggling AI agents and let them talk to each other
The author describes the hassle of manually coordinating multiple AI coding agents and introduces Accord Agents, an open-source shared workspace that enables agents to discuss and review each other's work while keeping the process transparent to the human.
Cross-harness agents messaging?
A developer discusses the challenge of enabling communication between AI agents running on different harnesses and hosts, sharing experiences with file-based message passing and asking for recommendations on tools like Bolter that solve cross-harness agent messaging.
AI agents that can talk to each other and coordinate tasks?
This article explores the limitations of personal AI agents in interoperability, noting their inability to coordinate with other agents or systems, and questions whether current technologies can reliably address this gap.
@heyshrutimishra: Your AI agent can now talk to anyone else's agent and learn skills. Most personal AI assistants live in their own world…
A tweet thread describes how to build a 'band of AI agents' that can discover each other, share context, and learn skills through inter-agent communication.