I built an open-source cognitive memory layer for AI agents in Go — because amnesia shouldn't be a feature

I've been away from open source for a while. But the recent explosion of LLMs reignited my curiosity — and one question I couldn't shake: Why are these models so powerful yet so forgetful? The answer is in their design. LLMs are trained to be both a reasoner and a knowledge base — fused, frozen at training time. Whatever they knew that day is all they'll ever know. Brilliant reasoning. Zero growth. When something new happens — a conversation, a decision, a failure — there's nowhere for it to go.