A new mobile development SDK for building AI apps uses small language models and personal data storage to keep everything on-device.

The New Stack is a publication covering trends and technologies in cloud-native development, DevOps, and software delivery. Developers can learn about containerization, Kubernetes, and cloud computing, as well as explore topics such as microservices architecture, serverless computing, and continuous integration/continuous delivery (CI/CD) pipelines.

The New Stack

DataSapien launched a mobile SDK for building on-device AI applications that processes data locally using small language models. The 20MB SDK includes a personal data store and supports iOS, Android, React Native, and Flutter through a low-code drag-and-drop interface. Unlike cloud-based approaches, all inference and personal data remain on the user's device, offering benefits in privacy, performance, and cost savings. Early use cases include retail and health apps, with the platform enabling decision-support functionality through orchestration of SLMs, ML algorithms, and deterministic rules. The company plans to extend support to web apps using WebAssembly.

New Mobile SDK Brings Low-Code Development to On-Device AI

Understanding the DataSapien SDK for On-Device AI

Use Cases and the Potential for Agentic AI

How DataSapien Compares to Google’s Web AI