LLM Memory: What Actually Works (And What Doesn't)

Fri, 10 Apr 2026 12:00:00 +0200

How I benchmarked my AI companion’s memory system against a viral open-source project — and what the numbers revealed about the state of LLM memory.

I’m building Tizenegy , an AI companion platform where users create and chat with customizable AI characters. One of the hardest problems in this space is memory — making the AI actually remember what you told it last week, last month, or six months ago.

Benchmarks on bjørn

LLM Memory: What Actually Works (And What Doesn't)