CareSync: A Local Health Memory Agent for Family Caregivers

This is a submission for the *Hermes Agent Challenge*: Build With Hermes Agent

What I Built

CareSync is a local health memory agent for student caregivers.

I'm Naomi, a 21-year-old engineering student. Between classes I help care for my grandma Kamala (78, high blood pressure, type 2 diabetes). I often forgot details from previous doctor visits, missed symptom patterns, and struggled to hand over care information to family members.

CareSync solves that with longitudinal memory. Symptoms, meals, vitals, medications, and reports are stored in a local SQLite database. The CLI can search history, identify patterns, and generate appointment summaries. Hermes Agent exposes the same capabilities through natural language.

What you get:

• One-line logging: ./caresync add "dizzy spell after lunch"
• Pattern search across weeks of history
• Medication tracking and report imports
• Doctor questions, appointment briefs, and handoff notes
• Full audit log of agent actions
• 7 Hermes skills mapped to real terminal commands
• Local-first design with no cloud storage

CareSync is not medical advice. It helps caregivers observe, organize, and prepare.

Demo

The demo walks through:

• Logging a new symptom
• Searching health history for recurring patterns
• Generating doctor questions and appointment briefs
• Using Hermes in natural language to query past events
• Reviewing the audit trail of actions taken

Example commands shown in the demo:

./caresync search --person Kamala --query dizziness
./caresync timeline --person Kamala
./caresync questions --person Kamala
./caresync brief --person Kamala --days 14
./caresync chat "has grandma been dizzy before?"

Code

Repository: https://github.com/Byte-Sized-Brain/caresync

Architecture

My Tech Stack

• Hermes Agent
• Python 3.12
• SQLite
• agentskills.io skill framework
• Terminal-based CLI
• Nous Portal

How I Used Hermes Agent

CareSync uses Hermes Agent as the orchestration layer between natural language and real caregiving workflows.

I created 7 Hermes skills that map directly to common caregiving tasks:

• Logging health events
• Searching symptom history
• Tracking medications
• Importing prescriptions and reports
• Generating appointment briefs
• Creating caregiver handoff notes
• Generating doctor questions

When a user asks something like:

Has grandma been dizzy before?

Hermes selects the appropriate skill, runs the underlying ./caresync command, analyzes the results, and returns a summary of relevant patterns found in the database.

The terminal tool was especially valuable because it allows Hermes to perform real actions instead of generating responses from memory. Every action writes to a local SQLite database and is recorded in an audit log, making the workflow transparent and inspectable.

Hermes also enables multi-step workflows. A request such as:

Prepare me for tomorrow's doctor appointment

can trigger multiple actions in sequence:

1. Search recent symptoms
2. Review medications
3. Generate doctor questions
4. Create an appointment brief

This turns a single natural-language request into a complete workflow.

Hermes was the right fit because caregiving is fundamentally a memory problem. The value comes from remembering events across weeks and months, identifying patterns, and helping caregivers prepare for important healthcare conversations. Hermes provides the reasoning and orchestration layer while CareSync provides the long-term memory and tools.