Saathi: A Tiered On-Device Large Language Model Architecture for Privacy-Preserving Mental Wellness on Mobile Devices

Read full text Summarise with VIRAT
Authors: Aviral Srivastava
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project presents Saathi, a Flutter-based mobile mental wellness application implementing a novel three-tier on-device LLM architecture for privacy-preserving support in the Indian context, featuring Hinglish-aware orchestration.

Fields of Study & Subjects

Digital Mental Health Interventions Privacy-Preserving Technologies in Data Mental Health via Writing

Publication details

Journal / source
OSF Preprints (OSF Preprints)
Publication date
17 March 2026
Language
EN
Document type
Preprint