Zero Cloud Spend: Running a Multi-Agent AI Lab on a Single Workstation
The full infrastructure stack behind five persistent AI agents — hardware, services, containers, networking, and why none of it costs anything beyond electricity.
Blog
Redesigning Resonance: What We Changed, What We Learned, and Where We Actually Are
The resonance system redesign — six phases of engineering, an argument about aversions that changed the design mid-session, and an honest assessment of where this work sits on the technology readiness scale.
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.
Building a Mind That Remembers: Operating Graph-Cortex
A deep dive into graph-cortex's operational reality — seven cortices, consolidation, the recall problem, habits, resonance, and what breaks. Real data from two experiments and seven agents.
Memory Systems for LLM Agents: A Survey and Comparison
A survey of how LLM agents handle persistent memory — from MemGPT's OS metaphor to Zep's temporal knowledge graphs — and where graph-cortex fits in the landscape.
Graph-Cortex: A Cognitive Architecture for Persistent AI Agent Identity
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.