Who should own your AI's memory of you?
This is a question that does not get asked enough.
Right now, if you use a hosted AI memory tool, your context, your decisions, your preferences, your project history, all of it lives on someone else's servers. Governed by their retention policies. Subject to their pricing changes. Potentially readable by their team.
That might be fine for some people. But for anyone working with sensitive information, proprietary code, or just wanting to know exactly where their data lives, it is a real concern.
We built Second Brain so that your memories live in your own Cloudflare account. We literally cannot access them. There is no Second Brain server that stores your data. The entire system runs on your infrastructure.
The tradeoff is real: you manage your own deployment. But with today's desktop app launch, that deployment is now five minutes of clicking through a setup wizard. No terminal. No git. No technical knowledge.
Your data. Your infrastructure. Your rules.
https://www.thesecondbrain.dev
We are live on Product Hunt today: https://www.producthunt.com/posts/second-brain-for-mac-and-windows
Where do you draw the line on what context you are comfortable storing with a third party versus keeping under your own control?
Replies
Dial
own-your-data is the right principle but I wonder how many people who'd benefit most from it will actually go set up their own Cloudflare account and keep it running. the security-conscious devs will do it happily, but the person with the most sensitive data might just be a non-technical founder who wants zero ops. is there a middle tier where you host it but encrypt so you can't read it, for people who want the privacy without the deployment work?
Dial
to actually answer the question you asked - for me the line is basically: anything that would be bad to leak stays local, everything else I don't think twice about. project decisions and preferences, fine wherever. proprietary code snippets or client details, no.
one thing I didn't see addressed yet though - own-your-infrastructure also means own-your-backup-and-uptime. if someone's Cloudflare account lapses, gets suspended, or they just forget to pay, what happens to the memory graph at that point? is there an export path so "your data, your infrastructure" doesn't quietly turn into "your data, gone" if the account side of things breaks
Second Brain for AI
Dial
@rahilpirani that's reassuring actually - free tier downgrade rather than a hard cutoff is a much better failure mode than I expected. one more edge case since we're here: account deletion (not just lapsed payment) - is there any grace period before data's gone, or does closing the Cloudflare account mean it's gone the moment that happens? not a criticism, just trying to figure out if I'd want a scheduled local export as a habit regardless of the answer.
Second Brain for AI
Dial
@rahilpirani fair enough, honest answer beats a confident guess. sounds like the takeaway either way is "export regularly and don't rely on the platform's cleanup behavior to save you" - which is probably the right default assumption for any hosted-on-someone-else's-infra setup regardless of what the actual answer turns out to be. appreciate you chasing it down though, curious if you find a definitive answer later.