Research & Open Source

The phone is the substrate.

DailyVox is built around a single hard invariant we call the Never-Leaves Guarantee: the user's journal content — audio, transcript, features, embeddings, model weights, and adapter parameters — never leaves the device, under any operating condition. The phone captures, transcribes, analyzes, stores, infers, trains, and speaks. The work below — a preprint, an open-source package, and two research reports — makes the architectural case.

16pp
arXiv systems paper
MIT
Swift package, 0 deps
CC BY 4.0
research reports
Zero
outbound bytes per entry

What we've published

Four primary artifacts. Each one stands alone and cross-references the others.

Open Source · Swift

DailyVoxTwin

Clean, dependency-free reference implementation of the personality-modeling engine described in the paper. MIT-licensed, zero third-party dependencies, multi-platform (iOS, macOS, visionOS, tvOS, graceful Linux fallback), Sendable-annotated for Swift 6, 7 passing tests, CI on macOS + Linux. The shipping app currently runs an in-tree copy of the same algorithms and will consolidate on this package in a near-term release.

~900 LOC Swift · SwiftPM · MIT
View on GitHub
Research Report · 3,000 words

The State of On-Device AI Journaling 2026

Analyst-grade snapshot of the category. How AI journaling apps collect, transmit, and process user data in 2026; the four-tier architectural classification; the economics shift from cloud to on-device; five concrete 2026–2027 forecasts.

Apr 17, 2026 · CC BY 4.0 · Citable
Read the report
Reference Data · 40 apps

The 2026 Journal App Privacy Audit

40 journal and AI-journal apps classified into four tiers by architecture, not policy. Includes observation methodology, vendor-response process, and citation-ready BibTeX. The reference the next journalist roundup will quote.

Apr 17, 2026 · CC BY 4.0 · 40 apps
Browse the audit

How to cite

All four artifacts are citation-ready. Copy the block that matches what you're referencing.

@misc{ng2026dailyvox, title = {DailyVox: An On-Device Framework for Privacy-Preserving Personality Modeling from Voice Diaries}, author = {Karthikeyan NG}, year = {2026}, note = {In preparation. Software: \url{https://github.com/intrepidkarthi/DailyVoxTwin}} }
Karthikeyan NG. The State of On-Device AI Journaling 2026. DailyVox Research Report, April 2026. https://getdailyvox.com/reports/state-of-on-device-ai-journaling-2026.html
Karthikeyan NG. The 2026 Journal App Privacy Audit. DailyVox Research Report, April 2026. https://getdailyvox.com/reports/journal-app-privacy-audit-2026.html

For press & researchers

If you're writing about on-device AI, privacy-preserving personal informatics, voice journaling, or Apple's Neural Engine / Foundation Models ecosystem — the four artifacts above are free to excerpt, translate, and republish with attribution (CC BY 4.0 where applicable; MIT for code).

Raw audit data (40 apps × 12 attributes), source LaTeX, benchmark methodology notes, or a quote for a piece you're working on: email . Responses within 48 hours.

Preferred author credit: Karthikeyan NG, independent researcher & author of DailyVox.