A local-first personal workspace — Diary, Planner, Finance, Library, Den, and AI — all running entirely on your machine.
No cloud. No API keys. No tracking. Your data stays on your device — always.
| Module | Description | AI |
|---|---|---|
| Diary | Private journaling with mood tracking | ✅ Ollama |
| Planner | Task management and daily planning | — |
| Finance | Personal expense and budget tracking | — |
| Library / Folio | Book notes and reading log | ✅ Ollama |
| Den / Nook | Personal creative space with ambient music | ✅ Ollama |
| Realm | Custom workspace for your projects | ✅ Ollama |
- 🔒 Fully local — all data stored in IndexedDB, nothing leaves your device
- 🦙 AI powered by Ollama — runs any local model (llama3, mistral, etc.)
- 🖥️ Desktop app — available as a native Electron app for Windows, Mac, and Linux
- 🌐 Web app — try it instantly at shabnam311.github.io/hive (AI requires local Ollama)
Visit shabnam311.github.io/hive — all features except AI work immediately in your browser. To enable AI, install Ollama locally (see below).
Prerequisites: Node.js 18+, npm
git clone https://github.com/shabnam311/hive.git
cd hive
npm install
npm run devOpen http://localhost:5173.
HIVE uses Ollama to run AI models locally — no OpenAI key, no subscriptions, no data sent anywhere.
- Download and install Ollama from ollama.com/download
- Pull a model:
ollama pull llama3
- Ollama runs as a background service — HIVE detects it automatically.
If Ollama isn't running, HIVE shows a setup guide. You can skip it and use all non-AI features normally.
# Dev mode with live reload
npm run electron:dev
# Build for your platform
npm run electron:build # current platform
npm run electron:build:win # Windows (.exe installer)
npm run electron:build:mac # macOS (.dmg)
npm run electron:build:linux # Linux (.AppImage)Builds output to the release/ folder.
| Layer | Technology |
|---|---|
| Frontend | React 19, TypeScript |
| Routing | TanStack Router (file-based) |
| Styling | CSS variables, custom design system |
| Data | IndexedDB (all local, no server) |
| AI | Ollama (local LLM inference) |
| Desktop | Electron 42 |
| Build | Vite 8 |
| Deploy | GitHub Pages |
hive/
├── src/
│ ├── routes/ # TanStack Router file-based routes
│ ├── components/
│ │ ├── ollama/ # OllamaSetup, OllamaModelPicker
│ │ └── ErrorBoundary.tsx
│ ├── services/
│ │ └── ollama.ts # Unified Ollama service (all AI calls)
│ └── db.ts # Unified IndexedDB data layer
├── electron/
│ ├── main.js # Electron main process
│ └── preload.js # Secure IPC bridge
├── public/ # Static assets
└── scripts/
└── make-404.mjs # SPA redirect for GitHub Pages
Contributions, issues, and feature requests are welcome! Feel free to open an issue or submit a pull request.
- Fork the repository
- Create a feature branch:
git checkout -b feat/your-feature - Commit your changes:
git commit -m "feat: add your feature" - Push to your branch:
git push origin feat/your-feature - Open a Pull Request
MIT © shabnam311