... first layer that needs to be EQUALLY READABLE BY MACHINES AND HUMANS (opinions are my own). I have done an extensive analysis of the current products in the space, some of which are heavily funded like Mem0 or supermemory . Current focus areas include making retrievals faster, hitting benchmarks, expanding the product surface (all valid problems). But they're all missing the human-agent interaction part. Right now, memory works like this: you give an context engine your memories ...

... agent forgets everything. The standard fix is cramming thousands of tokens of conversation history into every prompt. It's slow, expensive, and most of it isn't even relevant. So I looked at what's out there. Mem0, Zep, Supermemory. They all do basically the same thing: take text, embed it as blobs, throw it in a vector database. It works, sort of. But there's no structure. You can't look up a specific piece of knowledge ...

... smart people are already working on AI memory. Projects like Mem0 describe themselves as a universal memory layer for AI agents , focused on storing and retrieving user interactions so assistants can remember preferences and context over time. Supermemory pitches a scalable plug-and-play memory infrastructure and a Memory OS for AI apps, with APIs, SDKs and a Memory Router to attach persistent memory to any stack. I love that this space exists. But I also kept noticing a missing ...

... First thought is that memory is certainly useful. The fact that ChatGPT has long-term memory now is a huge lock-in factor for me. The exact form factor of the product is an open question. I like how @Supermemory is approaching it - and it seems they have some traction with their recent launches. This might be a good area to prototype around - build a bad version of all the different things you mention and try to use them ...