{"slug": "healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on", "title": "HealthHermes: A Private AI Health Companion That Remembers Everything and Runs on Your Own Machine", "summary": "A student developer from India built HealthHermes, a personal AI health companion that runs entirely on a user's local machine and remembers health history indefinitely. The tool allows users to log medications, symptoms, and clinical readings through natural conversation, then generates a complete health summary for doctor appointments without storing data in the cloud or requiring a subscription.", "body_md": "*This is a submission for the Hermes Agent Challenge: Build With Hermes Agent*\n\nI'm a student developer from India, and I built **HealthHermes** — a personal AI health companion that runs entirely on your own machine, remembers your health history forever, and helps you walk into every doctor's appointment actually prepared.\n\nHere's what triggered this idea for me.\n\nMy grandmother takes 4 medications a day. Every time she visits the doctor, she struggles to remember what she felt last week, which pill she started when, and whether her dizziness happened before or after she changed her dose. The doctor has 7 minutes. She forgets half of what she wanted to say. She leaves with half the answers she needed.\n\nThis happens to millions of people. Every single day.\n\nThe apps that exist either cost money, store your private health data on their servers, or make you fill out forms like you're doing tax returns. None of them actually *remember* you across sessions and get smarter over time.\n\nThat's exactly what Hermes Agent made possible. And that's exactly what HealthHermes does.\n\n**HealthHermes lets you just... talk:**\n\n\"I took my Metformin this morning\"\n\n\"Feeling dizzy and tired since 2 PM\"\n\n\"Blood sugar was 187 just now\"\n\n\"I have a doctor appointment tomorrow — give me my full summary\"\n\nFour sentences. A complete, structured health report — built from your own real logged data, saved on your machine, ready to print. No cloud. No subscription. No one reading your medical history.\n\n**What it does:**\n\nBelow is a real live session — database wiped clean before recording, every entry logged fresh in real time. No prior data, no hallucination, just the agent working.\n\n**Here's the exact terminal output from today's session:**\n\n**Step 1 — Logging a medication:**\n\n```\n● I took my Metformin 500mg with breakfast this morning\n\n  📚 skill     health-logger\n  💻 python3 log_entry.py --type medication --description \"Metformin 500mg\" --notes \"taken with breakfast\"\n\n╭─ ⚕ Hermes ───────────────────────────────────────────╮\n  Got it! I've logged your Metformin 500mg taken with\n  breakfast. Timestamp: 2026-05-31 08:12.\n  Is there anything else to add for this morning?\n╰───────────────────────────────────────────────────────╯\n```\n\n**Step 2 — Logging a symptom:**\n\n```\n● I've been feeling unusually tired and dizzy since 2 PM today\n\n  📚 skill     health-logger\n  💻 python3 log_entry.py --type symptom --description \"tired and dizzy\" --notes \"since 2 PM\"\n\n╭─ ⚕ Hermes ───────────────────────────────────────────╮\n  Noted — tiredness and dizziness logged since 2 PM today.\n  That sounds uncomfortable. Have you had enough water\n  today? And what was your blood sugar reading, if you\n  have it handy?\n╰───────────────────────────────────────────────────────╯\n```\n\n**Step 3 — Logging a clinical reading:**\n\n```\n● My blood sugar reading was 187 mg/dL just now, higher than usual\n\n  📚 skill     health-logger\n  💻 python3 log_entry.py --type note --description \"blood sugar 187 mg/dL\" --notes \"higher than usual\"\n\n╭─ ⚕ Hermes ───────────────────────────────────────────╮\n  Logged — blood sugar 187 mg/dL, noted as higher than\n  your usual. I'll make sure this appears prominently\n  in your doctor summary. Do mention this tomorrow.\n╰───────────────────────────────────────────────────────╯\n```\n\n**Step 4 — The wow moment: Doctor Summary**\n\n```\n● I have a doctor appointment tomorrow, generate my complete health summary now\n\n  📚 skill     doctor-summary\n  💻 python3 generate_summary.py --days 30\n\n╭─ ⚕ Hermes ───────────────────────────────────────────╮\n  Here's your health summary for tomorrow:\n\n  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n  Health Summary — 2026-05-31\n  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n  Current Medications:\n  • Metformin 500mg — taken with breakfast\n\n  Symptoms Logged:\n  • Tiredness and dizziness — since 2 PM today\n\n  Clinical Readings:\n  • Blood sugar: 187 mg/dL (noted as higher than usual)\n\n  Questions to Ask Your Doctor:\n  • My blood sugar was 187 mg/dL — should I adjust\n    my medication or diet?\n  • I experienced dizziness after taking Metformin —\n    is this a known side effect?\n  • Are my current medications still appropriate?\n\n  Saved to: ~/healthhermes_summary_2026-05-31.md\n╰───────────────────────────────────────────────────────╯\n```\n\nFour messages. A medication log, a symptom, a clinical reading, and a complete doctor-ready summary with auto-generated questions. All logged live. All stored locally. All from just talking naturally.\n\n**GitHub Repository:** [[https://github.com/HarithaB2005/HealthHermes](https://github.com/HarithaB2005/HealthHermes)]\n\nThe whole project is open source. Here's what's inside:\n\n```\nhealthhermes/\n├── SOUL.md                          ← who HealthHermes is and how it speaks\n├── install.sh                       ← one command sets everything up\n├── skills/\n│   ├── health-logger/\n│   │   ├── SKILL.md                 ← teaches Hermes when and how to log\n│   │   └── scripts/\n│   │       ├── log_entry.py         ← writes structured entries to SQLite\n│   │       └── query_logs.py        ← reads history + detects patterns\n│   └── doctor-summary/\n│       ├── SKILL.md\n│       └── scripts/\n│           └── generate_summary.py  ← builds the full doctor report\n└── cron/\n    └── healthhermes.yaml            ← medication reminders via Telegram\n```\n\n**Want to run it yourself? Three steps:**\n\n```\n# 1. Install Hermes Agent\ncurl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash\n\n# 2. Clone HealthHermes and install skills\ngit clone https://github.com/har/healthhermes.git\ncd healthhermes && chmod +x install.sh && ./install.sh\n\n# 3. Start talking\nhermes\n```\n\nThat's it. No Docker. No cloud setup. No API keys for health services. Just Hermes running locally.\n\n| Layer | Tool |\n|---|---|\n| Agent framework | Hermes Agent (Nous Research) |\n| AI model | Gemini 2.5 Flash via Google AI Studio (free tier) |\n| Health data storage | SQLite — local, private, yours |\n| Custom skills | Python 3 (log_entry.py, generate_summary.py, query_logs.py) |\n| Medication reminders | Telegram Bot via Hermes gateway |\n| Platform | Windows WSL2 + Ubuntu |\n\nHonestly? I tried to think of another way to build this and I couldn't. Here's why Hermes was the only framework that made HealthHermes possible:\n\n**1. Persistent Memory — the entire point of the product**\n\nEvery health app I've used forgets you the moment you close it. Hermes doesn't. It writes to `MEMORY.md`\n\nand `USER.md`\n\nautomatically and injects them into every session's system prompt. That means HealthHermes remembers your medications, your recurring symptoms, and your patterns across weeks — without me writing a single line of memory management code. This isn't a feature I added. It's just how Hermes works.\n\n**2. The Skill System — teaching the agent to think, not just execute**\n\nThis blew my mind when I first understood it. Instead of writing orchestration code telling the agent *what to do step by step*, I wrote two markdown files (`SKILL.md`\n\n) that describe *when* a skill is relevant and *how* to use it. When you say \"my back hurts,\" Hermes reads the health-logger skill description, decides on its own that this is a symptom log, and runs the Python script. No explicit command. No button press. Just natural conversation triggering real tool use.\n\nThat's actual agentic behavior — not a chatbot with if-else statements.\n\n**3. Cron Scheduler + Telegram — infrastructure I didn't have to build**\n\nMedication reminders are a critical feature for chronic illness patients. Building this from scratch would mean a separate service, a separate process, separate monitoring. With Hermes, I wrote a 20-line YAML file (`healthhermes.yaml`\n\n) defining three cron jobs, and Hermes's built-in scheduler picked it up automatically — firing Telegram messages at 8 AM and 9 PM daily. That's real infrastructure I got for free.\n\n**4. SOUL.md — the most important file in the project**\n\nFor a health app, getting the personality wrong isn't just bad UX — it's potentially harmful. I used `SOUL.md`\n\nto define HealthHermes as a warm, empathetic companion with hard limits: never diagnose, never alarm, never give dosage advice. Every single interaction is filtered through that identity. Judges can read the SOUL.md file in the repo — it's 24 lines that define everything the agent is allowed to be.\n\n**What surprised me most while building this:**\n\nThe moment HealthHermes started cross-referencing past entries and saying things like *\"I notice your dizziness appeared again today — this is the second time this week, both times in the afternoon\"* — that wasn't me writing pattern detection logic. That was Hermes reading the `recent_similar`\n\ndata my skill returned and reasoning over it naturally.\n\nIt stopped feeling like a project and started feeling like something genuinely useful.\n\nThat's the Hermes difference. And that's why I built HealthHermes.\n\n*HealthHermes is not a medical device and does not provide medical advice. Always consult a qualified healthcare professional for diagnosis and treatment.*", "url": "https://wpnews.pro/news/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on", "canonical_source": "https://dev.to/bezawada_haritha_dfab7cbf/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on-your-own-machine-4fa6", "published_at": "2026-05-31 07:54:24+00:00", "updated_at": "2026-05-31 08:11:33.974340+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "ai-agents", "artificial-intelligence", "natural-language-processing"], "entities": ["HealthHermes", "Hermes Agent", "India", "Metformin"], "alternates": {"html": "https://wpnews.pro/news/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on", "markdown": "https://wpnews.pro/news/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on.md", "text": "https://wpnews.pro/news/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on.txt", "jsonld": "https://wpnews.pro/news/healthhermes-a-private-ai-health-companion-that-remembers-everything-and-runs-on.jsonld"}}