Awesome GitHub RepositoriesDomain Models

This project is an AI agent workflow framework and development toolkit designed for AI-driven software engineering. It provides a system of modular instructions, prompt libraries, and standardized routines to orchestrate complex engineering sequences and automate the decomposition of plans into technical tasks. The system differentiates itself through advanced context management and prompt engineering, using state compression and handoff documents to preserve conversation history between different AI sessions. It employs a structured library of prompt skills and high-signal trigger words to e

This project is a full-stack web framework designed for building database-backed applications through a standardized architectural pattern. It provides a comprehensive suite of integrated libraries that manage the entire request-response lifecycle, from routing incoming web traffic to rendering dynamic server-side templates. By utilizing an object-relational mapping layer, the framework allows developers to define domain models that map database tables directly to application objects, simplifying data persistence, schema migrations, and complex relationship management. The framework is distin

This project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i

This project provides a framework for managing multi-agent systems, designed to automate complex software development, infrastructure, and business workflows. It functions as a multi-agent workflow orchestrator that routes tasks to domain-specific workers while maintaining state persistence and infrastructure automation. By leveraging large language models, the system decomposes high-level objectives into actionable plans, ensuring that complex operations are executed with consistency and reliability. The framework distinguishes itself through its hierarchical agent registry and policy-driven

This project is a comprehensive template for building enterprise-grade applications using clean architecture principles. It provides a structured foundation that decouples core business logic from infrastructure concerns, ensuring that domain entities remain independent of specific frameworks or database implementations. By utilizing a mediator-based request dispatching pattern, the system separates state-mutating commands from read-only queries, promoting a clean separation of concerns across the entire codebase. The architecture is organized into vertical slices, grouping related logic and

This is a reference implementation of Uncle Bob's clean architecture for Android, structured into distinct domain, data, and presentation layers. The project demonstrates how to organize an Android application around business use cases, keeping domain logic and entities free from framework dependencies. The architecture enforces dependency inversion through layered separation, where inner domain layers define interfaces that outer layers implement. This approach enables repository abstractions for data source switching, presenter-view separation for testable UI logic, and use-case composition

This project is a community-driven academic resource index and knowledge base dedicated to the study of transfer learning and domain adaptation. It functions as a curated repository of scholarly materials, including academic papers, tutorials, datasets, and benchmarks, designed to support research into how machine learning models apply knowledge from one task to another. The repository organizes these resources into a hierarchical taxonomy to facilitate the discovery of specialized methodologies. By leveraging distributed version control, the project maintains an evolving archive of research

This project is an integrated software suite and graphical workbench designed for capturing, visualizing, and reverse engineering wireless communication protocols and digital waveforms. It functions as a platform for software-defined radio analysis, enabling the recording of raw radio frequency data from hardware devices to facilitate the investigation of unknown or proprietary communication logic. The software distinguishes itself through a protocol-agnostic data modeling approach that represents radio transmissions as abstract bitstreams, decoupling analysis tools from specific modulation o

YSDA course in Natural Language Processing

This project is a software engineering style guide and a curated collection of architectural patterns and coding standards. It provides a multi-language coding standard to ensure maintainable software across Ruby, Python, JavaScript, and Swift. The project establishes a development workflow specification for version control, continuous integration, and peer review to maintain a linear project history. It also includes a web accessibility framework based on ARIA and WCAG standards, using design tokens and semantic HTML patterns to build inclusive interfaces. The guides cover a broad range of

Keras-GAN is a collection of generative adversarial network implementations built with Keras for synthetic data generation and image manipulation. It provides frameworks for image-to-image translation, image inpainting, and neural image super-resolution. The library includes tools for learning disentangled latent space representations to control specific attributes of synthetic outputs. It also features capabilities for image domain translation using paired or unpaired data and the ability to fill corrupted or missing image parts by analyzing surrounding visual context. The project covers ge

Este proyecto proporciona estándares arquitectónicos y patrones para organizar aplicaciones Django. Define una guía de arquitectura de proyectos centrada en desacoplar la lógica de negocio de las vistas y modelos a través de una arquitectura de capa de servicio. La guía establece patrones de diseño específicos, incluyendo una capa de servicio para funciones de lógica de negocio independientes y un patrón de selector de datos para aislar consultas complejas a la base de datos. Define un estándar para vistas de propósito único que delegan la lógica a servicios y utilizan serializadores dedicados para la entrada y salida de datos. El framework cubre varias áreas de capacidad más amplias, incluyendo gestión de configuración modular para separar las sobrescrituras de entorno de la configuración base, una jerarquía de excepciones personalizada para el mapeo de errores impulsado por el dominio y un sistema para coordinar tareas en segundo plano y programación periódica. También incluye estándares para combinar restricciones de base de datos con validación a nivel de modelo y servicio.

EconML es una biblioteca de Python para inferencia causal diseñada para estimar efectos de tratamiento heterogéneos utilizando una combinación de aprendizaje automático y econometría. Sirve como kit de herramientas para calcular efectos de tratamiento promedio condicionales para determinar cómo las intervenciones específicas impactan a individuos o subgrupos. El proyecto proporciona un framework para el aprendizaje automático doble y el aprendizaje automático ortogonal para aislar señales causales de factores de confusión de alta dimensión. Incluye implementaciones especializadas para bosques causales y aprendices de variables instrumentales, lo que permite la recuperación de relaciones causales incluso en presencia de factores de confusión no observados. La biblioteca cubre una amplia gama de capacidades, incluyendo la validación de modelos causales mediante pruebas de refutación y curvas de calibración, la construcción de políticas de tratamiento personalizadas y el análisis de regímenes de tratamiento dinámicos. También admite la inferencia estadística para la cuantificación de la incertidumbre y la interpretación de la heterogeneidad del efecto utilizando modelos basados en árboles y valores de Shapley. El proyecto se implementa y demuestra principalmente a través de Jupyter Notebooks.

Este proyecto es una librería integral para transfer learning y adaptación de dominio en visión artificial. Sirve como un framework para alinear distribuciones de características entre datasets de origen y destino, un kit de herramientas para la generalización de dominio y una librería para el aprendizaje semisupervisado utilizando pequeños datasets etiquetados y grandes conjuntos no etiquetados. La librería proporciona capacidades especializadas para la adaptación de dominio no supervisada, incluyendo el uso de redes adversarias, arquitecturas basadas en discrepancia y traducción de imagen a imagen para reducir el desajuste de distribución. También incluye herramientas para la generalización de dominio para garantizar la fiabilidad del modelo en dominios de destino no vistos a través de mezcla de estilos y minimización de riesgo invariante. El proyecto cubre una amplia superficie de capacidades, incluyendo la adaptación de tareas y el ajuste fino con regularización especializada, entrenamiento semisupervisado mediante pseudo-etiquetado y aprendizaje de consistencia, y selección de modelos de transfer learning utilizando métricas de transferibilidad. También incluye un gestor de datasets para automatizar la adquisición y preparación de benchmarks de visión estandarizados. La librería incluye utilidades para el monitoreo y la observabilidad, como visualizaciones t-SNE y métricas A-distance para analizar distribuciones de características y discrepancia de dominio.

This project is a Java microservices reference implementation that demonstrates the application of structural design patterns for distributed systems. It consists of a suite of containerized services and infrastructure dependencies designed to showcase how to coordinate multiple independent services into a functional system. The implementation focuses on several advanced architectural patterns, including a centralized API gateway for routing and aggregating responses, Command Query Responsibility Segregation to separate read and write operations, and event sourcing to persist the state of bus

This project serves as a comprehensive educational resource for implementing modular monoliths and microservices within .NET environments. It focuses on applying domain-driven design principles to manage complex business logic, providing a structured approach to building systems that can evolve alongside changing requirements. The architecture is defined by its emphasis on modularity and clear boundaries, utilizing vertical slices and bounded contexts to organize code by business process rather than technical layer. It distinguishes itself through a systematic migration framework that allows

AWS Powertools for Python is a utility framework designed for building production-ready Python functions on AWS Lambda. It provides a comprehensive suite of tools for observability, event parsing, routing, and idempotency management to streamline the development of serverless applications. The project distinguishes itself through specialized capabilities for event-driven architectures and AI agent orchestration. It enables the implementation of AI agents by exposing functions as tools via OpenAPI schemas and managing conversation states. Additionally, it features an idempotency library that p

POT is an optimal transport library providing a collection of solvers for computing Wasserstein, Gromov-Wasserstein, and Fused Gromov-Wasserstein distances between probability distributions. It functions as a differentiable tensor framework that integrates with various tensor libraries to enable automatic differentiation and GPU acceleration. The project is distinguished by its ability to align data distributions across different metric spaces by comparing internal relational structures rather than coordinates. It implements mathematical optimization algorithms as differentiable layers, allow

Commanded is an Elixir framework designed for building event-sourced applications that utilize domain-driven design. It provides a structured environment for implementing command-query responsibility segregation, allowing developers to separate write-side command processing from read-side data projection. By treating state changes as an immutable sequence of events, the framework ensures a reliable audit trail and facilitates system recovery. The project distinguishes itself through its support for distributed process orchestration and event-driven middleware pipelines. It enables the managem

Este proyecto es una implementación de referencia para estructurar aplicaciones Java utilizando arquitectura limpia y principios de diseño impulsado por el dominio (DDD). Proporciona una plantilla para organizar el código en capas concéntricas, asegurando que las reglas de negocio principales y las entidades de dominio permanezcan completamente independientes de frameworks externos, bases de datos y mecanismos de entrega. La arquitectura se basa en el principio de inversión de dependencia para desacoplar la lógica de negocio de la infraestructura. Al definir interfaces abstractas para el acceso a datos y servicios externos, el sistema permite el reemplazo de tecnologías subyacentes sin requerir modificaciones en la lógica principal de la aplicación. Una capa de configuración dedicada gestiona la inyección de dependencias, aislando el cableado específico del framework del código de dominio. La base de código admite una estrategia de pruebas integral que valida el comportamiento del sistema en múltiples niveles, incluyendo lógica unitaria aislada, escenarios de aceptación centrados en el negocio y viajes de extremo a extremo. Este enfoque modular facilita el mantenimiento a largo plazo al asegurar que las acciones de negocio permanezcan encapsuladas como unidades independientes y comprobables.