Your tasks, calendar, habits, and notes are stored in SQLite on your device. Sync is optional (iCloud or file bridge) and explicitly enabled.
Local data. Explicit AI boundary. Auditable changes.
Trust here comes from clear boundaries, not brand promises.
Lorvex should feel trustworthy because the system boundary is clear, not because the product makes vague promises.
The trust model is simple: your data stays on your device, the AI boundary is explicit, the code is open source, and every AI action is logged.
The full app, MCP server, and website are open source. Every claim maps to auditable code.
Lorvex has no built-in AI model. Your AI assistant connects through MCP — an external, explicit boundary you control.
Model
What this means in practice
These claims are intentionally narrow. They describe the boundary the product is designed around.
- Storage
- Planning data is stored on your device in SQLite. No cloud account required.
- Boundary
- No built-in model runtime. AI assistants connect through external MCP clients and operate through explicit tools.
- Open source
- Core code is open source and auditable on GitHub.
- Audit trail
- Every AI-initiated change is recorded in an auditable changelog you can review in the app.
- Telemetry
- No behavioral analytics. No tracking. The app does not phone home.
FAQ
Common questions
Does Lorvex include its own AI model?
No. AI capabilities come from external assistant clients (like Claude) connected through MCP.
Is AI required to use Lorvex?
No. Lorvex works as a complete standalone task manager. AI integration is optional.
Can data leave the device?
Only through paths you explicitly enable: iCloud sync, file bridge sync, or manual export.
Can I see what the AI changed?
Yes. Every AI operation is logged in a changelog visible in the app's Settings.
Inspect