Private silicon memory · On-device AI · iOS 26

When inspiration strikes, make it yours to keep.

AI can generate almost anything — but a fleeting spark belongs only to you. IdeaNook captures text, photos, and voice into private silicon memory on your iPhone. Offline capture, local AI, zero cloud.

Download on App Store

iOS 26.0+ · Android coming soon

When inspiration strikes, make it yours to keep.

Every format, understood

Type, snap, or hold to talk — voice memos become searchable transcripts, photos get on-device semantic descriptions.

Dual-track on-device AI

Apple Intelligence on supported devices with zero download, or Gemma 4 E2B as a full offline fallback.

Privacy by design

No network permission. Data never leaves your phone — not even for AI inference.

Chat-style capture

As simple as texting yourself

When inspiration strikes, just send it. Text, photos, and voice all flow into one idea stream — each understood and preserved on your iPhone.

Jot it down
Text

Jot it down

Send a thought the moment it arrives — natural as a chat, instantly searchable.

Photo

Snap what you see

From camera or library in one second. On-device AI generates a semantic description you can search and categorize.

Hold to talk, get a transcript
Voice

Hold to talk, get a transcript

Hold to record, release to send. Speech-to-text runs on-device — transcripts appear in the bubble and are fully searchable.

On-device auto-categorization

Send and forget — AI files it for you

Text, voice transcripts, and image descriptions — all categorized on-device. No waiting, no data leaving your phone.

On supported devices, choose Apple Intelligence in Settings → AI Engine — no model download needed. On other devices, download Gemma once (~2.4 GB) to enable AI. See setup guide

1

Send

Write down any thought

2

Sorting

A “⏳ sorting” chip appears

3

Tagged

Turns into a real category tag

4

Browse

See all ideas of one kind

10 smart categories, all inferred locally

💼Work
📖Study
🏠Life
Ideas
💻Tech
❤️Health
$Finance
👥Social
✈️Travel
Other
AI summaries

Text, voice, and photos — all in your digest

Richer summaries that weave together everything you captured. Every digest is generated on-device — the content never leaves your phone.

Automatic weekly digest

Automatic weekly digest

A Sunday-evening notification reminds you; reopen the app to auto-generate last week's review — text, transcripts, and image descriptions included.

Trigger anytime

Trigger anytime

Today, this week, or a custom range — generate a summary whenever you want.

Summarize from here to now

Summarize from here to now

Long-press any message to build a tailored review spanning any time period.

Liquid Glass input

An input bar redesigned for iOS 26

Built on iOS 26's native Liquid Glass — three elements flow and breathe as one. Hold to talk with live speech-to-text; the transcript lands right in your message bubble.

  • Native .glassEffect() fluid material
  • Text/voice modes switch with SF Symbol replace animation
  • Hold to talk with on-device transcription in the bubble
Privacy First

Your thoughts stay on your phone

Privacy isn't a feature — it's the baseline. IdeaNook makes data leaks architecturally impossible.

Zero network requests

The app requests no network permission, so it simply cannot upload data.

Data never leaves

Everything lives in the app sandbox; even system backups stay under your control.

AI runs locally

Apple Intelligence or Gemma 4 E2B — whichever engine you choose, inference stays on your iPhone with no cloud API.

Minimal permissions

Photos write-only, microphone & camera on demand — used then released.

Your thoughts stay on your phone
Under the Hood

Dual-track, all on-device

Apple Intelligence when available, Gemma when needed — plus system Speech and Vision for transcription and image understanding. We keep the complexity so you get the smoothness.

01

Apple Intelligence path

Foundation Models for categorization and summaries — zero model download on supported devices.

02

Gemma 4 E2B offline fallback

Google's on-device multimodal LLM via LiteRT-LM — full AI on any compatible iPhone.

03

On-device speech-to-text

Apple Speech framework transcribes voice memos locally — language packs managed by iOS.

04

On-device image understanding

Vision analysis + local LLM generates semantic descriptions for your photos.

05

SwiftUI + SwiftData

An all-Apple native stack using the latest iOS 26 APIs, including Liquid Glass.

06

Local SwiftData sandbox

All data stays in the app sandbox, with optional encrypted iCloud backup.

Your inspiration, embodied

Capture comes first. Download IdeaNook — private silicon memory that lives only on your iPhone.

Download on App Store