4 Repos
Implementations for connecting mobile applications to large language models for generative features.
Distinct from Android Integrations: Focuses specifically on generative AI and LLM integration rather than general multimodal or voice agent capabilities.
Explore 4 awesome GitHub repositories matching mobile development · Generative AI Integrations. Refine with filters or upvote what's useful.
This repository provides a collection of starter templates, reference projects, and implementation guides for integrating Firebase services into Android applications. It serves as a boilerplate for building mobile apps with built-in cloud backend integration. The project includes examples for connecting Android applications to large language models for generative AI features. It also provides sample code for managing user identity and authentication, as well as demonstrations for integrating cloud databases and serverless functions. The codebase covers a broad range of capabilities, includin
Provides implementation examples for connecting Android applications to large language models for generative AI features.
This is a Backend as a Service SDK for Apple platforms, providing a collection of libraries that connect iOS and macOS applications to cloud databases, authentication services, and serverless infrastructure. It serves as a developer kit for integrating real-time data synchronization, file storage, and push notifications into native apps. The SDK is distinguished by its generative AI integration, which routes text and multimodal prompts between on-device models and cloud-hosted large language models. It further differentiates itself with a specialized app distribution tool for managing pre-rel
Routes text and multimodal prompts between on-device models and cloud-hosted large language models.
lollms-webui ist eine webbasierte Benutzeroberfläche und ein lokaler KI-Modell-Orchestrator, der für die Interaktion mit und die Verwaltung von Large Language Models und multimodaler KI auf lokaler Hardware konzipiert ist. Es fungiert als generative KI-Multimedia-Suite, die die Erstellung von Text, Bildern, Video und Musik durch integrierte Diffusions- und Sprachmodelle ermöglicht. Das Projekt bietet einen dedizierten Persona-Manager zur Konfiguration von Verhaltensprofilen und distinkten Persönlichkeiten, die Stil und Tonfall der Modellantworten steuern. Es enthält ein lokales Speichersystem zur Aufrechterhaltung des langfristigen Konversationskontexts und der Chat-Historie über einen persistenten Speichermechanismus. Das System deckt breite Funktionen ab, einschließlich dynamischem Prompt-Routing zur Inferenz-Optimierung, GPU-Beschleunigung und einem modularen Binding-System zur Verknüpfung mit lokalen oder entfernten Modellanbietern. Es bietet zudem Tools zur Visualisierung von KI-Denkprozessen, zur Verwaltung von Chat-Historien in einer lokalen Datenbank und zur Erweiterung der Schnittstelle über ein Plugin-basiertes Tool-System. Das Deployment wird durch containerisierte Images unterstützt, um eine konsistente Ausführung über verschiedene Betriebssysteme hinweg sicherzustellen.
Directs prompts to specific models based on task complexity, cost, or speed to optimize performance.
This project is a full-stack development framework designed for building cross-platform mobile applications that integrate generative language and image models. It provides a pre-configured boilerplate and a collection of tools to accelerate the creation of intelligent software, including support for interactive chat interfaces and visual content generation. The framework distinguishes itself by incorporating a server-side proxy layer that centralizes authentication and authorization, ensuring secure communication when interacting with external AI services. It also features a modular styling
Builds cross-platform mobile applications that integrate large language models and image generation services.