I Built a Cross-Platform Memory Layer for AI Agents Using Ebbinghaus Forgetting Curves
I use Claude Code, Cursor, and Codex daily. And every single one of them forgets who I am between sessions. I'd tell Claude Code I prefer Python for backend work. Three sessions later, it suggests ...

Source: DEV Community
I use Claude Code, Cursor, and Codex daily. And every single one of them forgets who I am between sessions. I'd tell Claude Code I prefer Python for backend work. Three sessions later, it suggests TypeScript. I'd set up a project structure in Cursor, switch to Codex for a quick fix — and it has no idea what I'm working on. Each tool has its own isolated memory, and none of them talk to each other. I tried the usual fixes. Dumped context into a vector store. Built a RAG pipeline. It worked — until the store had hundreds of entries and a two-year-old preference outranked something I said yesterday, just because the phrasing matched better. The retrieval had no sense of time. That's when I started reading about Hermann Ebbinghaus. A 140-year-old experiment that changes everything In 1885, a German psychologist named Hermann Ebbinghaus spent years memorizing nonsense syllables — things like "DAX," "BUP," "ZOL" — and testing how quickly he forgot them. His results produced one of the most r