Machine Learning

PaddlePaddle is a comprehensive industrial deep learning platform that provides a complete ecosystem of frameworks, model libraries, and development tools. It supports advanced capabilities such as automatic parallelism, unified training and inference, and high-order differentiation for scientific computing. The platform is designed to facilitate AI commercialization across various sectors by offering a flexible, high-performance architecture for diverse model development.

Tabby is a self-hosted, open-source AI coding assistant designed as an on-premises alternative to GitHub Copilot. It operates as a self-contained system that does not require external cloud services or database management. The platform supports consumer-grade GPUs and offers an OpenAPI interface for seamless integration with existing development infrastructure.

DeepEP is a high-performance communication library designed for modern machine learning training and inference, specifically focusing on expert parallelism. The library utilizes a lightweight Just-In-Time compilation module and the NCCL Gin backend to deliver high-throughput, low-latency GPU kernels. It supports advanced features like pipeline parallelism and remote memory access while significantly reducing SM resource consumption compared to previous versions.

PaddlePaddle is a comprehensive industrial deep learning platform that provides core frameworks, model libraries, and end-to-end development tools. It supports advanced features like unified dynamic and static graphs, automatic parallelism, and high-order differentiation for scientific computing. The platform is designed to facilitate large-scale model training and inference across diverse industrial sectors.

Thinking with Visual Primitives introduces a novel approach to Multimodal Large Language Models by interleaving spatial markers directly into the reasoning process. This method addresses the reference gap in complex structural tasks by anchoring abstract language to concrete physical coordinates. The framework achieves frontier-competitive performance while maintaining high visual token efficiency through a compressed architecture.

RuView is an edge-based sensing platform that utilizes WiFi Channel State Information (CSI) to detect human presence, vital signs, and activities without the need for cameras or wearables. The system processes radio signal disturbances through low-cost ESP32 hardware to provide real-time spatial intelligence and environment mapping. It supports advanced features like 3D point cloud generation, pose estimation, and persistent data storage using local neural networks.

This comprehensive guide provides a detailed walkthrough of the Hermes Agent framework developed by Nous Research. It covers core mechanisms like the self-improving learning loop, memory systems, and automated skill evolution across seventeen chapters. The book serves as a practical resource for developers and AI enthusiasts looking to implement and customize their own intelligent agents.

Secret Llama is an entirely in-browser chatbot that allows users to run open-source models like Llama 3 and Mistral locally. Because the application operates directly within the browser, all conversation data remains private and no server installation is required. The platform provides a user-friendly interface that functions offline while leveraging WebGPU technology for performance.

KittenTTS is an open-source, lightweight text-to-speech library designed for efficient voice synthesis on CPUs. It offers multiple model sizes ranging from 15M to 80M parameters, ensuring high-quality 24 kHz audio output with minimal disk footprint. The library includes built-in text preprocessing and supports adjustable speech speeds for versatile integration.

Pipcook is a modular JavaScript application framework designed to help front-end engineers integrate machine learning into their workflows. It provides a comprehensive pipeline system that allows users to train, validate, and deploy machine learning models directly within the Node.js environment. By bridging access to Python packages, the framework enables developers to leverage powerful machine learning tools without requiring deep expertise in the field.

Index-AniSora is a comprehensive open-source system developed by Bilibili for high-quality anime video generation. The project provides a controllable generation model, a specialized data processing pipeline, and an evaluation benchmark tailored for animation aesthetics. It supports advanced features such as character 3D video generation, video style transfer, and multimodal guidance to facilitate diverse animation production tasks.

OpenDataLoader PDF is a high-performance, open-source parser designed to convert PDF documents into structured formats like Markdown, JSON, and HTML for AI and RAG pipelines. It features a hybrid processing mode that combines deterministic local parsing with AI-driven analysis to achieve industry-leading extraction accuracy for complex tables, formulas, and scanned documents. Additionally, the project provides automated accessibility solutions, including end-to-end Tagged PDF generation compliant with international standards.

LiteRT-LM is a high-performance, production-ready inference framework designed by Google for deploying Large Language Models on edge devices. It supports a wide range of platforms including Android, iOS, desktop, and IoT, while leveraging GPU and NPU hardware acceleration for optimal performance. The framework enables advanced capabilities such as multi-modality and function calling, powering on-device AI experiences in various Google products.

Pipcook is a JavaScript application framework designed to enable front-end engineers to utilize machine learning without requiring extensive prior knowledge. The project provides a modular pipeline architecture that supports the entire lifecycle of model training, validation, and deployment. It also includes a bridge to Python, allowing developers to leverage mature Python machine learning libraries directly within the Node.js runtime.

Pairec is a Go-based web framework designed to accelerate the development of online recommendation services. It utilizes JSON-based configurations to streamline the setup and deployment of complex recommendation logic. The framework includes various built-in model functionalities to simplify the creation of efficient recommendation systems.

CorridorKey is a neural network-based tool designed to solve the complex problem of unmixing foreground subjects from green or blue screen backgrounds. It reconstructs the true straight color and linear alpha channel for every pixel, effectively preserving fine details like hair and motion blur. The project supports high-fidelity VFX workflows by outputting 16-bit and 32-bit Linear float EXR files compatible with industry-standard compositing software.

This comprehensive guide provides a practical walkthrough of the Hermes Agent, an open-source AI framework developed by Nous Research. The book details the agent's unique architecture, which features a self-improving learning loop, a three-layer memory system, and automated skill evolution. It covers seventeen chapters ranging from foundational concepts and installation to real-world applications and advanced agent orchestration.

The PaddlePaddle community serves as a central hub for developers to contribute to the framework through code improvements, documentation, and presentations. It provides structured governance, specialized working groups, and various mentorship programs to support active participation. Contributors are recognized through official certifications, release notes, and inclusion in the project's authorship records.

Kronos is an open-source decoder-only foundation model specifically designed to analyze and forecast financial K-line sequences. It utilizes a two-stage framework that quantizes multi-dimensional market data into hierarchical tokens before processing them through an autoregressive Transformer. The project provides a comprehensive suite of pre-trained models and tools for both direct forecasting and domain-specific fine-tuning.

AI Engineering from Scratch is a comprehensive 320-hour curriculum that guides students from fundamental linear algebra to building autonomous agent swarms. The course emphasizes an AI-native learning approach where students use AI coding agents to test their knowledge and build reusable tools throughout 20 distinct phases. By working across Python, TypeScript, Rust, and Julia, learners develop a professional portfolio of prompts, skills, and agents that can be deployed in real-world environments.

This repository provides a comprehensive educational framework for building agent harnesses, which are the essential environments that allow AI models to perceive and act. It argues that true agency is learned by models during training, while the developer's role is to construct the tools, knowledge, and context management systems that enable these models to function. Through twelve progressive sessions, users learn to build robust, scalable agent architectures by reverse-engineering the principles behind Claude Code.