ideAI

Active

A mirror with memory

Your phone is the most trusted device you own. ideAI treats it that way — all intelligence runs on-device. You journal, it reflects. It finds patterns in your thinking you didn't know were there. Auto-tagging, semantic search, multi-note synthesis. Military-grade encryption, zero cloud dependency.

inference

3 backends

platform

iOS

On-device

Swift SwiftUI MLX SwiftData Foundation Models Bedrock

ideaapp.com →(coming soon) App Store →

// WHY ON-DEVICE

The cyberpunk inversion already happened. Your phone's Secure Enclave is the most trusted computing environment you own — more than your laptop, infinitely more than any cloud. ideAI builds on that foundation. Every model runs locally via MLX. Your journal entries never leave the device. The AI that understands your thinking patterns is yours alone.

// WHAT IT DOES

Semantic search across all your notes — under 500ms, entirely on-device
Auto-tagging via embeddings — under 100ms per note
Multi-note synthesis: the AI reads 10-20 of your notes and surfaces patterns you missed
AES-256-GCM encryption with biometric unlock (Face ID / Touch ID)
MCP server integration — Claude can read your journal with your permission

// IN ACTION

ideAI MCP connection and Data Shard Mode

ideAI semantic search across journal entries

Data Shard Mode — MCP server integration with Claude.

Semantic search across all your notes — entirely on-device.

Atlas — explore your thinking patterns over time.

// ARCHITECTURE

16 Swift packages organized by feature. Each module builds and tests independently. The app coordinates three inference tiers — routing between them automatically based on availability, device capability, and task priority.

┌─────────────────────────────────────────────────────┐
│                     ideAI App                       │
│                                                     │
│  ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌────────┐  │
│  │  Notes   │ │  Search  │ │Synthesis │ │  Atlas  │  │
│  │ Feature  │ │ Feature  │ │ Feature  │ │  /Graph │  │
│  └────┬─────┘ └────┬─────┘ └────┬─────┘ └───┬────┘  │
│       │            │            │            │       │
│  ┌────▼────────────▼────────────▼────────────▼────┐  │
│  │            InferenceCoordinator                │  │
│  │         (priority queue + preemption)          │  │
│  └──────┬──────────────┬──────────────┬───────────┘  │
│         │              │              │              │
│  ┌──────▼─────┐ ┌──────▼─────┐ ┌──────▼──────┐      │
│  │ Foundation │ │  MLX Swift  │ │ AWS Bedrock │      │
│  │  Models    │ │ 19 models   │ │  (Claude)   │      │
│  │ (Apple AI) │ │ 350M → 8B  │ │   cloud     │      │
│  └────────────┘ └────────────┘ └─────────────┘      │
│                                                     │
│  ┌──────────────────┐  ┌─────────────────────────┐  │
│  │ SwiftData (dual) │  │ AES-256-GCM + Keychain  │  │
│  │ iCloud │ Local    │  │ Face ID / Touch ID      │  │
│  └──────────────────┘  └─────────────────────────┘  │
└─────────────────────────────────────────────────────┘

Three inference tiers with priority-based coordination. User-facing ops always preempt background tasks.

// KEY DECISIONS

Priority-based inference coordination — conversation preempts compression, preventing OOM on a phone with a single GPU
Dual-store SwiftData — user content syncs to iCloud, regenerable data (embeddings, caches) stays local
Native Apple embeddings first, MLX fallback — zero app-size cost for semantic search on supported devices
Swift 6 strict concurrency across all 16 modules — data races caught at compile time, not in production
MCP server built in — Claude can read your journal with your permission, over an encrypted WebSocket tunnel