Awesome GitHub RepositoriesRuntime Resource Sharing

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

RealtimeSTT is a local speech-to-text engine and real-time automatic speech recognition server. It utilizes transformer-based recognition and omnilingual pipelines to convert live audio streams into text, providing a WebSocket-based streaming API for raw PCM audio transmission. The project is distinguished by a dual-backend transcription pipeline that uses a lightweight engine for immediate partial suggestions and a heavier model for final high-accuracy results. It includes a wake word detection system to trigger recording and employs a shared-resource inference model to distribute heavy spee

Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

Agent-OS is an LLM multi-agent orchestration framework and AI software development lifecycle tool designed to coordinate specialized agents through shared workspaces and structured task lists. It functions as an agentic application bootstrapper and technical specification engine, providing the infrastructure to guide the process from product requirements to automated coding and deployment. The system distinguishes itself through spec-driven development, using detailed technical specifications and layered context injection to ensure generated code aligns with project standards. It employs a ma

Oh-my-agent 是一个与供应商无关的编排框架，旨在管理自主智能体团队并自动化复杂的工程工作流。它作为一个多智能体开发工具，在不同的开发环境和命令行界面之间同步智能体行为、技能和特定于项目的规则。 该平台通过基于配置的投影脱颖而出，它为映射到各种供应商特定运行时格式的智能体定义维护了单一事实来源。通过利用跨平台符号链接桥接和与供应商无关的技能注册表，它确保了模块化、可重用的功能在无论使用何种底层 AI 编码助手或 IDE 时都能保持一致。 该系统提供了一套全面的工具来管理智能体生命周期，包括用于代码导航的语义索引、用于管理令牌消耗的资源受限执行防护栏，以及用于安全和合规性的自动化质量门禁。它支持通过基于意图的触发器编排多步骤任务，允许在定义的工作流中调度维护作业和执行外部二进制文件。 配置通过集中式配置文件和自动同步进行管理，确保项目环境之间的一致性。该系统旨在作为基础层进行安装和初始化，用于自动化仓库内的开发、研究和基础设施任务。