Posts tagged under Multi-Agent
One agent trying to be everything hits a ceiling that looks exactly like burnout. The 7-week journey from generalist amnesia to a crew of 7 that argues in ticket comments — and why the arguing is the point.
Read more →Your reviewer starts fresh every run. Forgets everything you fixed. Flags the same issues again. That sounds broken until you realize a reviewer with memory inherits every hallucination. The reset is the feature. Here's how 7 rounds became a clean pass.
Read more →Seven AI agent profiles. One Linux box. A SQLite kanban board that routes work between them. No cloud service, no SaaS dashboard — just profiles, personas, and a local dispatch system. Here's how to build your own crew.
Read more →Let's talk about your goals and how codegrit<span class="accent">.dev</span> can help you move work forward.