# Suggested open-source stack

> Project: "Mobile app with a local LLM and voice input"
> Built from the ideas catalog (https://ideas.asveas.com). Each section is a detected need with the best-fitting repos, strongest first.

## LLM / AI model
- [mudler/LocalAI](https://github.com/mudler/LocalAI) — LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. (★50.3k, Go, vibe 93/100) · details: https://ideas.asveas.com/r/mudler/LocalAI
- [unslothai/unsloth](https://github.com/unslothai/unsloth) — Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. (★79.3k, Python, vibe 95/100) · details: https://ideas.asveas.com/r/unslothai/unsloth
- [vercel/ai](https://github.com/vercel/ai) — The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents (★27.9k, TypeScript, vibe 90/100) · details: https://ideas.asveas.com/r/vercel/ai

## Local / private AI
- [unslothai/unsloth](https://github.com/unslothai/unsloth) — Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. (★79.3k, Python, vibe 95/100) · details: https://ideas.asveas.com/r/unslothai/unsloth
- [ollama/ollama](https://github.com/ollama/ollama) — Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★187k, Go, vibe 99/100) · details: https://ideas.asveas.com/r/ollama/ollama
- [open-webui/open-webui](https://github.com/open-webui/open-webui) — User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★158k, Svelte, vibe 98/100) · details: https://ideas.asveas.com/r/open-webui/open-webui

## Image / audio / video
- [huggingface/transformers](https://github.com/huggingface/transformers) — 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. (★169k, Python, vibe 98/100) · details: https://ideas.asveas.com/r/huggingface/transformers
- [pydantic/pydantic-ai](https://github.com/pydantic/pydantic-ai) — How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. (★21.1k, Python, vibe 88/100) · details: https://ideas.asveas.com/r/pydantic/pydantic-ai
- [coqui-ai/TTS](https://github.com/coqui-ai/TTS) — 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production (★46.2k, Python, vibe 68/100) · details: https://ideas.asveas.com/r/coqui-ai/TTS

## Mobile app
- [expo/expo](https://github.com/expo/expo) — An open-source framework for making universal native apps with React. Expo runs on Android, iOS, and the web. (★53.5k, TypeScript, vibe 93/100) · details: https://ideas.asveas.com/r/expo/expo
- [react/react-native](https://github.com/react/react-native) — A framework for building native applications using React (★127k, C++, vibe 97/100) · details: https://ideas.asveas.com/r/react/react-native
- [flutter/flutter](https://github.com/flutter/flutter) — Flutter makes it easy and fast to build beautiful apps for mobile and beyond (★181k, Dart, vibe 98/100) · details: https://ideas.asveas.com/r/flutter/flutter

## Also worth a look
- [BerriAI/litellm](https://github.com/BerriAI/litellm) — The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] (★63.1k, Python, vibe 94/100) · details: https://ideas.asveas.com/r/BerriAI/litellm

---
Refine: https://ideas.asveas.com/stack?q=Mobile%20app%20with%20a%20local%20LLM%20and%20voice%20input · API: https://ideas.asveas.com/api/stack?q=Mobile%20app%20with%20a%20local%20LLM%20and%20voice%20input&format=md