I got tired of telling ChatGPT who I am, then switching to Claude and starting from zero. Then Gemini. Your history lives on three different companies' servers and none of them talk to each other.
So I built MEMMEM (Windows for now, Mac/Linux planned). It imports the official data exports from ChatGPT, Claude and Gemini into a local SQLite memory on your own machine, and exposes a local MCP server. Any MCP-capable assistant (Claude Code, Codex, Gemini CLI...) can query it and gets back the exact message, its date and its source - not a hallucinated summary. So every new AI you open starts with your full context instead of a blank slate.
Fully local: no accounts, no telemetry, no cloud, no tokens. There is an optional analyst that runs on Ollama entirely on-device. Uninstalling deletes everything, because there is no server-side copy.
I am not a developer by trade - I built it with AI coding assistants because I wanted it for myself. Happy to go into the architecture (the MCP bridge, the consent model) if anyone is curious.
[link] [comments]