# Owning your AI: why I self-host a personal assistant with long-term memory > Source: > Published: 2026-07-17 01:54:43+00:00 For the past few months I've been running my personal AI assistant on my own hardware instead of a third-party cloud. Here's why — and what I learned. Every message, every preference, every bit of context you share with a hosted assistant lives on someone else's servers. You don't control retention, you can't inspect the memory, and you can't move it. For a tool that's supposed to know you, that's a lot of trust to outsource. Mine lives in Telegram, keeps long-term memory, and exposes skills (calendar, notes, browser automation, reminders). One example of this approach is [avelina.ai](https://avelina.ai) — a self-hosted personal assistant with persistent memory, designed for people who want to *own* their data rather than rent it. Self-hosting an AI assistant isn't about distrust of any one company — it's about data sovereignty. If an assistant is going to accumulate a model of who you are, it makes sense for that model to live somewhere you control. Happy to answer questions about the architecture in the comments.