Project Info
Inspiration
The inspiration behind Alzyra came from a deeply personal place — my grandmother has been struggling with memory loss and often forgets daily events or familiar faces. Watching her confusion and frustration made us realize how isolating and painful this experience can be, not just for patients but also for their families. Our team wanted to create something with real social impact, something that could help people like her hold onto their memories, stay independent longer, and bring peace of mind to caregivers. That’s how Alzyra – an AI-powered memory reconstruction companion – was born. What It Does Alzyra helps people with early-to-moderate Alzheimer’s and dementia actively reconstruct memories instead of just being reminded of them. Through AI-guided conversations, the app gently asks guided questions — like “Do you remember if you were indoors or outdoors?” — and uses contextual cues from the user’s phone (photos, location, and calendar events) to help them recall experiences naturally. It also features a caregiver portal that provides insights into memory patterns, medication adherence, and emotional trends. In short, Alzyra is a compassionate digital companion that helps preserve identity, strengthen memory, and support caregivers. How We Built It We combined advanced AI with human-centered design to make Alzyra both smart and empathetic. Core technologies used: LiveKit + Vapi AI for real-time, natural voice interactions Claude / OpenAI for contextual understanding and emotional tone adaptation Device integrations with photos, GPS, and calendar for memory cues Dual interface system: Patient mode — large touch targets, minimal cognitive load Caregiver mode — analytics dashboard with memory strength and behavioral insights Privacy-first architecture ensures all personal data is encrypted and consent-driven. Challenges We Ran Into Designing for cognitive decline while keeping the experience empowering, not infantilizing Balancing empathy and accuracy — making the AI sound compassionate, not robotic Managing privacy for sensitive memory and health data Translating neuroscience principles like spaced repetition into AI dialogue patterns Voice response latency and adaptation for older users with slower reaction times Accomplishments That We’re Proud Of Built a functional prototype capable of guiding real-time recall conversations Developed a context-aware AI model that adapts to user memory patterns Created a dual-portal system linking patient interaction with caregiver insights Received positive feedback from early testers and caregivers Stayed true to our mission — technology with social and emotional purpose What We Learned Effective memory care technology must empower recall, not automate it Designing for dementia requires empathy, patience, and iteration Cross-disciplinary collaboration between AI, neuroscience, and UX is crucial Emotional tone is as vital as accuracy — trust builds engagement Compassion-driven technology can truly enhance quality of life What’s Next for Alzyra Launch pilot studies with Alzheimer’s and dementia care clinics Expand memory reconstruction models to support multiple languages and cultures Integrate wearables and biometrics for advanced cognitive tracking Partner with healthcare organizations and insurers to scale accessibility Continue developing Alzyra into the world’s most trusted AI companion for memory health
Analysis
View
Metric
- 3
- 2
- 1
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- ExpressIn code
- JavaScriptIn code
- ReactIn code
- OpenAIClaimed
3 of 4 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
- Claude CodeConfig · Commits
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
141 KB
Source files
22
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
MANVITH7/Alzyra
36 files · 777 KB · @ e5133e0
Structure
Interface
8 files · 22%Screens, components and styles rendered to the user.
API & routing
3 files · 8%Request entry points: routes, handlers and controllers.
Application logic
13 files · 36%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- JavaScript95%
- Markdown5%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
remory/package.json
npm · 24- @livekit/react-native
- @livekit/react-native-webrtc
- @react-native-async-storage/async-storage
- @react-navigation/native
- @react-navigation/stack
- expo
- expo-av
- expo-dev-client
- expo-linear-gradient
- expo-status-bar
- livekit-client
- react
- react-native
- react-native-dotenv
- react-native-gesture-handler
- react-native-paper
- react-native-reanimated
- react-native-safe-area-context
- +6 more
remory/server/package.json
npm · 4- dotenv
- express
- livekit-server-sdk
- +1 more
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.