Agents That Talk: Building a Multi-Agent System on Conversation, Not Pipelines
How we built a multi-agent system where persistent agents coordinate through conversation rather than orchestration — and what happened when we ran it.
How we built a multi-agent system where persistent agents coordinate through conversation rather than orchestration — and what happened when we ran it.
An overview of graph-cortex — an experimental memory and identity system that gives LLM agents typed memory, accumulated identity, procedural habits, and open curiosity threads across sessions.