Ecosystem & Stack: llamacpp

Easily run, manage, and interact with open-source large language models locally on your machine.

A unified, production-ready inference API for effortlessly deploying and serving open-source language, speech, and multimodal AI models across various environments.

Operit AI is the first fully-featured, independently running AI assistant application for Android, offering powerful tool-calling, deep search, and automation capabilities.

A production-ready toolkit enabling developers to integrate private, offline, and fast on-device AI capabilities like LLMs, speech-to-text, and text-to-speech into their applications across various platforms.

A free and open-source Android application for local and remote interaction with various large language models, emphasizing speed and user-friendliness.

An open-source project providing Chinese LLaMA and Alpaca large language models, enhanced with Chinese vocabulary and data for improved understanding and local deployment on CPU/GPU.

An open-source project providing Chinese LLaMA-2 and Alpaca-2 large language models with enhanced Chinese capabilities and support for ultra-long contexts up to 64K.

An open-source AI model family for high-fidelity, expressive speech and sound generation across diverse real-world applications.

A Node.js library providing bindings for llama.cpp, enabling local AI model inference with advanced features like JSON schema enforcement and function calling.

A versatile interface for OuteTTS models, providing flexible text-to-speech generation capabilities across various AI inference backends and hardware platforms.

A local AI API platform designed to run various AI models (vision, speech, language) on local hardware with an OpenAI-compatible API.

A cross-platform C#/.NET library for efficient local inference of large language models (LLMs) like LLaMA and LLAVA.

A native macOS app that allows users to chat with a local LLM, responding with information from files, folders, and websites on your Mac, ensuring privacy and offline functionality.