Apex SDK for building Model Context Protocol (MCP) servers natively in Salesforce

spring java based a2ui server

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

fast tts (ZH EN) lightweight

🗺️ Generate City 3D map with R3F. Include building and road information.

Overview of Secure-Launch process on Qualcomm devices

🦞 Turn any Android phone into a 24/7 AI server — one command, zero hassle. No proot, no Ubuntu, pure Termux.

Easily interact with ChromaDB Vector Database in C++

A modern runtime for JavaScript and TypeScript.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Grafika test app

lightweight, standalone C++ inference engine for Google's Gemma models.

Speech-to-text server framework with next-gen Kaldi

Android设备与设备之间通过Wifi P2P 技术进行文件传输，覆盖广，速度快，并且不会消耗网络流量。

全维度的前沿大语言模型自动化评测套件。涵盖逻辑推理、智能体编程、网页特效代码生成以及百万Token级长文本解析（GPT-5.4 / Claude 4.7 / DeepSeek-V4 等）

Modern C++ Apache Kafka client library (wrapper for librdkafka)

C++ ggml runtime hub for multilingual ASR models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment via NeMo Forced Aligner-style CTC, and others. Fork of…

Open-Source Frontier Voice AI

Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 servers, webs…

The Generative UI framework

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

基于whisper.cpp的Android语音识别Demo应用

LLM inference in C/C++

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

AI-powered assistant to help you with your daily tasks, powered by Llama 3, DeepSeek R1, and many more models on HuggingFace.

Native A2UI Renderer for iOS/Android/HarmonyOS — high performance streaming AI-generated UI with 22 built-in components. The only complete 3-platform A2UI implementation.