MiniMind is a modular training guide for Large Language Models (LLMs), aiming to help developers deeply understand the training mechanism of modern large language models such as Llama and GPT through concise code and comparative experiments. It prioritizes principles over operations, provides experiments for each design choice, consists of 6 independent modules from basic components to complete architecture, and offers low entry barriers for learning. Suitable for individuals preparing for jobs in large model fields, students/researchers in machine learning/deep learning, developers, and learners with basic PyTorch knowledge who seek a deep understanding of LLMs. Not suitable for complete beginners, users only interested in deploying models quickly without caring about principles, and those looking for production-level code and best practices.

PromptHub is a versatile tool for generating prompts and ideas to spark creativity and overcome writer's block. It provides a wide range of customizable prompts and exercises to inspire writers, artists, educators, and anyone looking to enhance their creative thinking. With PromptHub, users can access a diverse collection of prompts across various categories such as writing, drawing, brainstorming, and more. The tool offers a user-friendly interface and allows users to save and share their favorite prompts for future reference. Whether you're a professional writer seeking inspiration or a student looking to boost your creativity, PromptHub is the perfect companion to ignite your imagination and enhance your creative process.

Snap-Solver is a revolutionary AI tool for online exam solving, designed for students, test-takers, and self-learners. With just a keystroke, it automatically captures any question on the screen, analyzes it using AI, and provides detailed answers. Whether it's complex math formulas, physics problems, coding issues, or challenges from other disciplines, Snap-Solver offers clear, accurate, and structured solutions to help you better understand and master the subject matter.

VocoType is a free desktop voice input method designed for professionals who value privacy and efficiency. All recognition is done locally, ensuring offline operation and no data upload. The CLI open-source version of the VocoType core engine on GitHub is mainly targeted at developers.

The ai_quant_trade repository is a comprehensive platform for stock AI trading, offering learning, simulation, and live trading capabilities. It includes features such as factor mining, traditional strategies, machine learning, deep learning, reinforcement learning, graph networks, and high-frequency trading. The repository provides tools for monitoring stocks, stock recommendations, and deployment tools for live trading. It also features new functionalities like sentiment analysis using StructBERT, reinforcement learning for multi-stock trading with a 53% annual return, automatic factor mining with 5000 factors, customized stock monitoring software, and local deep reinforcement learning strategies.

Cockpit Tools is a versatile AI IDE account management tool that supports Antigravity, Codex, GitHub Copilot, Windsurf, and Kiro. It allows efficient management of multiple AI IDE accounts with features like one-click switching, quota monitoring, automatic wake-up, and parallel running of multiple instances. The tool supports 16 languages and provides functionalities such as dashboard overview, account management for each supported platform, multiple instance management, quota monitoring, wake-up tasks, device fingerprinting, and plugin integration.

UnitySkills is an AI-driven Unity editor automation engine based on REST API. It allows AI to directly control Unity scenes through Skills. The tool offers extreme efficiency with Result Truncation and SKILL.md slimming, a versatile tool library with 282 Skills supporting Batch operations, ensuring transactional safety with automatic rollback, multiple instance support for controlling multiple Unity projects simultaneously, deep integration with Antigravity Slash Commands for interactive experience, compatibility with popular AI terminals like Claude Code, Antigravity, Gemini CLI, and support for Cinemachine 2.x/3.x dual versions with advanced camera control features like MixingCamera, ClearShot, TargetGroup, and Spline.

LunaBox is a lightweight, fast, and feature-rich tool for managing and tracking visual novels, with the ability to customize game categories, automatically track playtime, generate personalized reports through AI analysis, import data from other platforms, backup data locally or on cloud services, and ensure privacy and security by storing sensitive data locally. The tool supports multi-dimensional statistics, offers a variety of customization options, and provides a user-friendly interface for easy navigation and usage.

This repository provides a comprehensive guide to large language models (LLMs), covering various aspects such as training, fine-tuning, compression, and applications. It includes detailed tutorials, code examples, and explanations of key concepts and techniques. The repository is maintained by Liguo Dong, an AI researcher and engineer with expertise in LLM research and development.

All Model Chat is a feature-rich, highly customizable web chat application designed specifically for the Google Gemini API family. It integrates dynamic model selection, multimodal file input, streaming responses, comprehensive chat history management, and extensive customization options to provide an unparalleled AI interactive experience.

VS Code extension for monitoring Google Antigravity AI model quotas. It provides a webview dashboard, QuickPick mode, quota grouping, automatic grouping, renaming, card view, drag-and-drop sorting, status bar monitoring, threshold notifications, and privacy mode. Users can monitor quota status, remaining percentage, countdown, reset time, progress bar, and model capabilities. The extension supports local and authorized quota monitoring, multiple account authorization, and model wake-up scheduling. It also offers settings customization, user profile display, notifications, and group functionalities. Users can install the extension from the Open VSX Marketplace or via VSIX file. The source code can be built using Node.js and npm. The project is open-source under the MIT license.

Chatless is a modern AI chat desktop application built on Tauri and Next.js. It supports multiple AI providers, can connect to local Ollama models, supports document parsing and knowledge base functions. All data is stored locally to protect user privacy. The application is lightweight, simple, starts quickly, and consumes minimal resources.

Torch-RecHub is a lightweight, efficient, and user-friendly PyTorch recommendation system framework. It provides easy-to-use solutions for industrial-level recommendation systems, with features such as generative recommendation models, modular design for adding new models and datasets, PyTorch-based implementation for GPU acceleration, a rich library of 30+ classic and cutting-edge recommendation algorithms, standardized data loading, training, and evaluation processes, easy configuration through files or command-line parameters, reproducibility of experimental results, ONNX model export for production deployment, cross-engine data processing with PySpark support, and experiment visualization and tracking with integrated tools like WandB, SwanLab, and TensorBoardX.

py-xiaozhi is a Python-based XiaoZhi voice client designed for learning through code and experiencing AI XiaoZhi's voice functions without hardware conditions. The repository is based on the xiaozhi-esp32 port. It supports AI voice interaction, visual multimodal capabilities, IoT device integration, online music playback, voice wake-up, automatic conversation mode, graphical user interface, command-line mode, cross-platform support, volume control, session management, encrypted audio transmission, automatic captcha handling, automatic MAC address retrieval, code modularization, and stability optimization.

LimCode is a powerful VS Code AI programming assistant that supports multiple AI models, intelligent tool invocation, and modular architecture. It features support for various AI channels, a smart tool system for code manipulation, MCP protocol support for external tool extension, intelligent context management, session management, and more. Users can install LimCode from the plugin store or via VSIX, or build it from the source code. The tool offers a rich set of features for AI programming and code manipulation within the VS Code environment.

Saber-Translator is your exclusive AI comic translation tool, designed to effortlessly eliminate language barriers and enjoy the original comic fun. It offers features like translating comic images/PDFs, intelligent bubble detection and text recognition, powerful AI translation engine with multiple service providers, highly customizable translation effects, real-time preview and convenient operations, efficient image management and download, model recording and recommendation, and support for language learning with dual prompt word outputs.

MiniMind is a modular training guide for Large Language Models (LLMs), aiming to help developers deeply understand the training mechanism of modern large language models such as Llama and GPT through concise code and comparative experiments. It prioritizes principles over operations, provides experiments for each design choice, consists of 6 independent modules from basic components to complete architecture, and offers low entry barriers for learning. Suitable for individuals preparing for jobs in large model fields, students/researchers in machine learning/deep learning, developers, and learners with basic PyTorch knowledge who seek a deep understanding of LLMs. Not suitable for complete beginners, users only interested in deploying models quickly without caring about principles, and those looking for production-level code and best practices.

This open-source course teaches how to build an advanced RAG and LLM system using LLMOps and ML systems best practices. It helps you create an AI assistant that leverages your personal knowledge base to answer questions, summarize documents, and provide insights. The course covers topics such as LLM system architecture, pipeline orchestration, large-scale web crawling, model fine-tuning, and advanced RAG features. It is suitable for ML/AI engineers and data/software engineers & data scientists looking to level up to production AI systems. The course is free, with minimal costs for tools like OpenAI's API and Hugging Face's Dedicated Endpoints. Participants will build two separate Python applications for offline ML pipelines and online inference pipeline.

Knavigator is a project designed to analyze, optimize, and compare scheduling systems, with a focus on AI/ML workloads. It addresses various needs, including testing, troubleshooting, benchmarking, chaos engineering, performance analysis, and optimization. Knavigator interfaces with Kubernetes clusters to manage tasks such as manipulating with Kubernetes objects, evaluating PromQL queries, as well as executing specific operations. It can operate both outside and inside a Kubernetes cluster, leveraging the Kubernetes API for task management. To facilitate large-scale experiments without the overhead of running actual user workloads, Knavigator utilizes KWOK for creating virtual nodes in extensive clusters.

reDB Node is a distributed, policy-driven data mesh platform that enables True Data Portability across various databases, warehouses, clouds, and environments. It unifies data access, data mobility, and schema transformation into one open platform. Built for developers, architects, and AI systems, reDB addresses the challenges of fragmented data ecosystems in modern enterprises by providing multi-database interoperability, automated schema versioning, zero-downtime migration, real-time developer data environments with obfuscation, quantum-resistant encryption, and policy-based access control. The project aims to build a foundation for future-proof data infrastructure.

MiniMind is a modular training guide for Large Language Models (LLMs), aiming to help developers deeply understand the training mechanism of modern large language models such as Llama and GPT through concise code and comparative experiments. It prioritizes principles over operations, provides experiments for each design choice, consists of 6 independent modules from basic components to complete architecture, and offers low entry barriers for learning. Suitable for individuals preparing for jobs in large model fields, students/researchers in machine learning/deep learning, developers, and learners with basic PyTorch knowledge who seek a deep understanding of LLMs. Not suitable for complete beginners, users only interested in deploying models quickly without caring about principles, and those looking for production-level code and best practices.

This repository provides a collection of interview questions and answers for algorithm engineers. The questions are organized by topic, and each question includes a detailed explanation of the answer. This repository is a valuable resource for anyone preparing for an algorithm engineering interview.

LLM-as-HH is a codebase that accompanies the paper ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution. It introduces Language Hyper-Heuristics (LHHs) that leverage LLMs for heuristic generation with minimal manual intervention and open-ended heuristic spaces. Reflective Evolution (ReEvo) is presented as a searching framework that emulates the reflective design approach of human experts while surpassing human capabilities with scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. The tool can improve various algorithms on problems like Traveling Salesman Problem, Capacitated Vehicle Routing Problem, Orienteering Problem, Multiple Knapsack Problems, Bin Packing Problem, and Decap Placement Problem in both black-box and white-box settings.

The Universal Numbers Library is a header-only C++ template library designed for universal number arithmetic, offering alternatives to native integer and floating-point for mixed-precision algorithm development and optimization. It tailors arithmetic types to the application's precision and dynamic range, enabling improved application performance and energy efficiency. The library provides fast implementations of special IEEE-754 formats like quarter precision, half-precision, and quad precision, as well as vendor-specific extensions. It supports static and elastic integers, decimals, fixed-points, rationals, linear floats, tapered floats, logarithmic, interval, and adaptive-precision integers, rationals, and floats. The library is suitable for AI, DSP, HPC, and HFT algorithms.

UmaAi is a tool designed for algorithm learning purposes, specifically focused on analyzing scenario mechanics in a game. It provides functionalities such as simulating scenarios, searching, handwritten-logic, and OCR integration. The tool allows users to modify settings in config.h for evaluating cardset strength, simulating games, and understanding game mechanisms through the source code. It emphasizes that it should not be used for illegal purposes and is intended for educational use only.