Yuki Nagai

ondevice-llm

by uny

Framework-agnostic on-device LLM inference with a unified OnDeviceGenerator API: single-shot and streaming generation, model download/progress tracking, systemInstruction handling, and simple cancellation semantics.

#llm

Android JVMKotlin/Native

Apache License 2.0

firebase-kotlin-sdk

by uny

Generative AI integration for Firebase offering model creation, content DSL, multi-turn chat with streaming, safety filters, Vertex AI backend support, and token-estimation tools.

#text, #service-sdk, #sdk, #llm, #chatbot, #apple

Android JVMKotlin/Native

Apache License 2.0

koog-firebase

by uny

Firebase Vertex AI integration enabling agent-framework LLM prompts with preconfigured Gemini model definitions, streaming responses, and simple executor adapters for easy backend connection.

#llm

Android JVMKotlin/Native

Apache License 2.0

koog-ondevice

by uny

Koog-compatible on-device LLM client enabling offline Gemini Nano and Apple Foundation Models inference without API keys, supports hybrid cloud fallback, model download, warm-up and routing.

#router, #llm, #kotlin-flow, #coroutines, #client, #apple, #ai

Android JVMKotlin/Native

Apache License 2.0