NobodyWho React Native Starter App
A React Native example app demonstrating NobodyWho, a library for running LLMs locally and efficiently on a phone, including chat, tool calling, vision, RAG, speech-to-text and text-to-speech.
This starter app demonstrates NobodyWho, a library for running large language models locally and efficiently on any device. It shows streamed chat responses from a local model, tool calling that gives the model access to custom functions, image and audio ingestion with a multimodal model, semantic search and reranking with an embedding model, speech-to-text transcription, and text-to-speech generation.
Models are downloaded from Hugging Face using hf:// URLs or plain HTTP(S) URLs and cached locally for reuse. Scripts are provided to fetch either a minimal chat-only model set for fast inference on older phones, or a larger multimodal set including Gemma for chat, vision, hearing, embeddings and reranking on flagship phones.
It is a TypeScript React Native project released under the EUPL-1.2 license.