Skip to content
2nd Place

Memento

Memento: Voice-Enabled Memory Care Assistant Memento helps individuals with memory loss maintain daily routines through empathetic voice interaction and visual monitoring.

Code Video Cerebral Valley

Core trick

A voice agent with custom camera and Notion tools checks medication selection from camera frames and logs adherence.

Tags

healthvoicevision

Description

Memento: Voice-Enabled Memory Care Assistant Memento helps individuals with memory loss maintain daily routines through empathetic voice interaction and visual monitoring. Our initial focus: medication management. What It Does Memento listens and watches. It processes conversations and camera feeds to provide timely reminders, verify correct medication selection, and detect emotional states for more compassionate interactions. All medication schedules and adherence logs sync with Notion. Technical Approach Built on Cartesia's voice agent platform, we extended their LlmAgent with: Custom tools for camera monitoring and Notion integration. An experimental wrapper architecture that processes images as continuous streams rather than tool calls. We explored two paradigms for multimodal agent design: discrete tool invocation versus continuous stream processing.
TanviBhardwaj24/memoryCatcher★ 00 forksPythonCreated Feb 7, 2026 · last push Feb 8, 2026

README excerpt

# Project Sentinel

A hybrid voice agent for dementia assistance that "sees" users via their local webcam while running AI logic in the cloud.

## Architecture

```
┌─────────────────────┐         HTTP/Ngrok         ┌─────────────────────┐
│   LOCAL LAPTOP      │◄──────────────────────────►│   CARTESIA CLOUD    │
│                     │                             │                     │
│  ┌───────────────┐  │    GET /snapshot            │  ┌───────────────┐  │
│  │ local_eyes/   │  │  ─────────────────────►     │  │ cloud_brain/  │  │
│  │ FastAPI       │  │                             │  │ Voice Agent   │  │
│  │ + Webcam      │  │  ◄─────────────────────     │  │ + Claude      │  │
│  └───────────────┘  │    {image_base64: ...}      │  └───────────────┘  │
│                     │                             │                     │
└─────────────────────┘                             └─────────────────────┘
```

## Components

### 1. Local Eyes (`/local_eyes`)
Lightweight FastAPI server running on the user's laptop that captures webcam frames.

- **Endpoint:** `GET /snapshot` - Returns Base64 encoded JPEG (512x512)
- **Port:** 8000

### 2. Cloud Brain (`/cloud_brain`)
Voice agent using the `line` framework with Claude Sonnet 4.5 for conversation and vision.

- **Tools:**
  - `look(focus)` - Captures image and analyzes with Claude Vision
  - `log_incident(event)` - Logs safety concerns (background task)
  - `end_call` - Ends the voice session

## Setup Instructions

### Prer

Team