My AI tools kept forgetting everything, so I gave them a shared brain (local + open source)

Hi there! this is my first small rant that turned into a project: every AI tool I use has its own memory. I tell Claude Desktop something, Cursor has no clue. New chat? Back to zero. It drove me nuts — so I built **Centralaizer**. This is an open source solution, so it's free with MIT license. It's a little memory hub that runs **on your own machine**. Any MCP tool (Claude Desktop, Cursor, Claude Code, VS Code Copilot…) plugs into it and they all share the same memory. Save a fact or a decision in one, the others can pull it right up. No cloud — everything stays on your laptop. A few things I cared about: * 🧠 **opt-in, not spying** — the agent decides what to save/recall * 🚧 **sketchy notes get held in a review queue** instead of polluting everyone's memory * 🔒 it **scrubs PII** (emails, keys, phones) before storing * 🔎 search isn't just keywords — vector + full-text + a little knowledge graph * 🖥️ a **web dashboard** to browse it all (light *and* dark mode 🌙) One command (`./setup_and_run.sh`) or Docker. There's also a Claude Code hook for auto-recall, one-click export, and a browser extension to bring it into ChatGPT/Gemini/Qwen. Would love thoughts — or roasts — on the retrieval and the "trust score" idea. Any feedback is more than welcome as it's an initial project. 🎥 *(attach centralaizer-demo.mp4)* · 👉 [https://github.com/lestercoyoyjr/Centralaizer-public](https://github.com/lestercoyoyjr/Centralaizer-public)