A self-hosted personal health AI agent for Apple Watch and iPhone.
HealthPython · SwiftGitHub @thinkweeOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
One-Stop Personal Health AI Agent "Say Hi to Healthy Me"
Translation pending
Taken from the repository README
Loading the full README.
Read the full README ↗HiMe (Health Intelligence Management Engine) is a self-hosted, fully local, secure, and open-source one-stop personal health AI agent platform. It understands your wearable health data in real-time and provides you with proactive insights 7/24, and of course, a cute pixel-art cat that serves as your personal health digital twin. Download the app at https://apps.apple.com/app/himeapp/id6762160735
News 📢 Our paper is now on arXiv and accepted as an EMNLP 2026 demo paper! 🎉🎉🎉 Check it out at: HiMe: A Self-Hosted Personal Health AI Agent Platform. Give it a read to learn more about the system design and motivation behind HiMe.
Three steps. Total time: ~10 minutes.
Skip this if you'll use the built-in in-app chat — the iOS app talks to the agent directly, no bot needed. If you'd rather chat over an IM app, HiMe also supports Telegram, Feishu, or WeChat. Pick one and grab the credentials before you start the server (the setup wizard will ask for them).
/start to @userinfobot → save your chat_id.WEIXIN_GATEWAY_ENABLED=true in .env, then run python -m backend.weixin.qr_login (or docker exec -it hime-backend python -m backend.weixin.qr_login) and scan the QR with WeChat → Settings → Plugins → ClawBot.Detailed walkthrough: docs/INSTALL.md#im-gateway-setup.
git clone https://github.com/thinkwee/HiMe.git HiMe
cd HiMe
./setup.sh
Don't worry, just follow the quick start wizard in setup.sh and all the steps will be done for you. ~2-5 minutes for first build.
When it's done, the dashboard is at http://localhost:5173 — but you'll do most things through the iOS app.
localhost, your Mac's LAN IP, or homelab.local).docs/INSTALL.md#ios-app.That's it. Open the Chat tab in the app and message Hime — or message your IM bot if you set one up — and the agent will reply.
Pull the latest release and restart — your .env, data/, and memory/ are preserved:
git pull
./hime.sh restart --rebuild # Docker mode: rebuilds images
./hime.sh restart --clean # Native mode: clears Python/node caches
If a new release adds variables, diff .env.example against your .env and fill in any missing keys. See docs/DEPLOYMENT.md for backup guidance.
docs/INSTALL.md — manual setup, native dev install, public deployment, customization.docs/DEPLOYMENT.md — LAN, public-internet, and Compose production patterns.docs/DEVELOPMENT.md — architecture, adding tools/providers, code style.CONTRIBUTING.md — contribution process.SECURITY.md — security disclosure.PRIVACY.md — privacy policy.HiMe is research-grade software for personal use. It is not a medical device and does not provide diagnoses.
HiMe is released under the PolyForm Noncommercial License 1.0.0.
"HiMe" and the HiMe logo are trademarks of the HiMe Organisation.