I Built VitaRecall: A Health AI Companion That Remembers Without Pretending to Be a Doctor

Health is too serious for an AI to pretend to be a doctor.

That is why I think health-related AI should start with a more careful role: helping people prepare for care, not diagnosing them, prescribing medication, or replacing emergency services.

I built VitaRecall, an AI care-preparation companion that helps patients:

• prepare questions before an appointment
• organise notes and care preferences
• keep track of follow-up tasks
• continue a conversation without repeating what matters to them

VitaRecall is built with Gemini and uses Walrus Memory on mainnet for patient-controlled continuity across new chats, browsers, devices, the web app, and Telegram.

How memory works

A user can share a preference such as:

“Use short, plain-language answers and remind me to write down questions for my appointment.”

VitaRecall archives that context automatically by default. When the user returns in a fresh conversation, the app searches that user’s own memory namespace, retrieves relevant saved context, and uses it to make the response more helpful.

The interface distinguishes a pending save from a confirmed Walrus receipt. Users can review storage receipts, open confirmed blob IDs in Walrus Scan, and pause future saving if they choose.

So far, VitaRecall has generated 35 unique confirmed Walrus mainnet blob IDs across its live app records.

Safety boundaries matter

VitaRecall is not a medical professional, diagnosis tool, prescription service, or emergency service. It is designed to support care preparation and continuity—not make clinical decisions.

The current public demo uses fictional information only. A key design goal is making memory useful while giving users a clear view of what is being saved and when it is recalled.

What I learned

Persistent memory changes the usefulness of a chatbot. The challenge is not merely storing text—it is making recall relevant, visible, user-controlled, and safe enough for a sensitive context.

I would genuinely value developer feedback:

• How would you design patient-controlled AI memory?
• What should a user be able to inspect before trusting a returning AI companion?
• How would you improve the boundary between useful support and unsafe health advice?

Live app: https://vitarecall.vercel.app
Telegram: https://t.me/VitaRecall_bot

Source code: https://github.com/Tolex081/vitarecall

Demo walkthrough: https://tinyurl.com/VitaRecall

Built for Walrus Sessions 8: Chatbots That Remember.