40 discoveries
Developed by ZEISS Microscopy, this repository provides a collection of Jupyter Notebooks designed to demonstrate the integration of ZEN software with Python. It serves as a practical guide for researchers and developers to handle CZI image files, extract metadata, and implement deep learning pipelines. The workshop covers essential tools like pylibczirw and czmodel, enabling users to bridge the gap between proprietary microscopy data and modern AI-driven image processing tasks.
LLMStudyGuide is an interactive web-based resource designed to help developers and researchers prepare for AI-focused technical interviews. Created by shanselman and based on Hao Hoang's comprehensive PDF, this tool features 50 curated Q&As covering LLMs, transformers, and NLP. It enhances the learning experience with extended context, external study resources, and built-in progress tracking, making it an essential companion for anyone looking to solidify their understanding of modern machine learning concepts.
The ai-agents-workshop by denniszielke is an educational repository designed to teach developers how to build and deploy AI agents. It provides practical, hands-on exercises covering industry-standard frameworks including LangChain, LangGraph, LlamaIndex, and Semantic Kernel. With a focus on Azure integration, this workshop serves as a structured guide for engineers looking to master agentic workflows, from basic orchestration to complex multi-agent systems.
yashsarode45/LangChain-LangGraph is an educational repository featuring a series of Jupyter notebooks designed to teach developers how to build sophisticated AI applications. Created by Yash Sarode, this resource focuses on the latest v1.x APIs for LangChain and LangGraph. It provides a structured learning path, starting from fundamental concepts and progressing to advanced agentic workflows and RAG implementations, making it an essential guide for those looking to implement modern LLM orchestration patterns.
Aronno1920/AI-Engineering is an immersive, 19-module study plan curated for developers. It bridges the gap between foundational theory and practical application, covering essential topics like LLMs, LangChain, computer vision, and explainable AI. The repository provides a structured roadmap for mastering modern AI engineering through hands-on projects and industry-standard tools.
Effective LLM Applications is a practical repository by wmeints that serves as a hands-on guide for C# developers. It focuses on leveraging Microsoft's Semantic Kernel to build robust AI solutions. The project covers essential concepts including Retrieval-Augmented Generation (RAG), structured output generation, tool calling, and rigorous testing strategies, providing developers with the patterns needed to move beyond simple prototypes into reliable, enterprise-grade AI software.
The dmcteknoloji/sql-server-2025-kitap is an open-source educational resource providing a deep dive into SQL Server 2025. Created by the DMC Teknolojisi community, this repository serves as a comprehensive handbook covering advanced database features, including DiskANN, vector embeddings, and RAG (Retrieval-Augmented Generation) workflows. It includes practical T-SQL code examples, errata, and community-driven Q&A, making it an essential reference for developers and database administrators looking to leverage AI capabilities within the Microsoft SQL Server ecosystem.
elisaterumi-ai/agent-skills-in-practice is an educational repository that demystifies the concept of AI agent skills. Created by elisaterumi-ai, it provides a structured framework for developers to design, organize, and deploy functional capabilities within LLM-based agent architectures. By bridging the gap between theoretical agent design and practical implementation, the resource helps engineers build more reliable and capable autonomous systems that can interact effectively with external tools and environments.
Developed by the Data Science for Social Good (DSSG) initiative at Carnegie Mellon University, this repository serves as the core curriculum for the ML for Public Policy Lab. It provides students and practitioners with practical Jupyter Notebooks and resources to bridge the gap between advanced machine learning techniques and complex social policy issues, focusing on data-driven decision-making for the public good.
This repository provides a comprehensive hands-on lab environment for developers looking to combine Neo4j's graph database capabilities with Google Cloud's AI ecosystem. Maintained by Neo4j-partners, the project offers structured tutorials and code examples to demonstrate how to leverage Gemini, Vertex AI, and Google Cloud infrastructure to build intelligent, graph-powered applications. It serves as a bridge for data scientists and engineers to implement advanced RAG (Retrieval-Augmented Generation) and machine learning workflows using graph-based context.
Created by Sebastian Raschka, this repository provides a practical, hands-on comparison of four popular automatic image augmentation methods: AutoAugment, RandAugment, AugMix, and TrivialAugment. Using Jupyter Notebooks, it demonstrates how these techniques function within the PyTorch ecosystem, offering researchers and developers a clear guide on how to improve model robustness and generalization through automated data preprocessing strategies.
The quarkus-langchain4j-workshop, created by Clement Escoffier, is a comprehensive educational resource for Java developers. It provides a structured path to integrating Large Language Models (LLMs) into enterprise applications using the Quarkus framework and the LangChain4j library. The repository includes practical exercises and code examples designed to help developers master AI orchestration, prompt engineering, and vector database integration within the Java ecosystem.
NDXDeveloper's formation-mariadb is a structured 20-module educational repository focused on MariaDB 12.3 LTS. It provides deep technical insights into SQL optimization, transactions, replication, and high-availability clusters using Galera and MaxScale. Crucially, it includes dedicated modules on MariaDB Vector, enabling developers to integrate database-native vector search capabilities for AI and RAG (Retrieval-Augmented Generation) workflows. This resource is designed for DBAs and DevOps engineers looking to master modern database infrastructure and AI-ready data management.
CodelyTV/ai-search_engine_with_rag-course is an educational repository designed to teach developers how to implement Retrieval-Augmented Generation (RAG) systems. Created by the CodelyTV team, the project provides hands-on examples for integrating AI search capabilities into applications. It focuses on leveraging PostgreSQL as a vector database using pgvector and pgai, enabling developers to build efficient, scalable search engines that combine traditional relational data with modern semantic search techniques using TypeScript.
Developed by yizhe-ang, k-means-explorable is an interactive web-based tool designed to demystify the K-Means clustering algorithm. Built with Svelte, it provides a visual, hands-on experience that allows users to manipulate data points and observe how centroids shift and clusters form in real-time. By transforming abstract mathematical concepts into an explorable interface, this project serves as an excellent educational resource for students and practitioners looking to grasp the fundamental mechanics of unsupervised machine learning.
Pragmatic AI is a comprehensive resource by Noah Gift that bridges the gap between machine learning theory and cloud-native implementation. It serves as a practical guide for developers and data scientists looking to leverage major cloud providers—AWS, Azure, and GCP—to build, scale, and deploy AI applications. The repository contains code examples, Jupyter notebooks, and architectural patterns that demonstrate how to integrate serverless technologies and cloud services into real-world machine learning workflows.
Intro-Course-AI-ML/LessonMaterials is an open-source repository providing a structured educational curriculum for students and beginners. Maintained by the Intro-Course-AI-ML community, it offers a collection of Jupyter Notebooks and lesson materials designed to teach core concepts in AI and machine learning. This resource serves as a foundational guide for those looking to build their technical skills through hands-on coding exercises and theoretical explanations, making high-quality AI education more accessible to the public.
The Microsoft IoT Curriculum is an open-source educational resource designed for students and educators. It provides structured, hands-on labs that cover the fundamentals of the Internet of Things (IoT), edge computing, and AI integration. Developed by Microsoft, the repository offers modular content suitable for universities, coding bootcamps, and community colleges, enabling learners to build real-world projects using Azure IoT services, Python, and hardware like the Raspberry Pi and NVIDIA Jetson.
AlphaGo Simplified is a companion repository for the 2024 CRC Press book by Mark H. Liu. It provides practical, educational implementations of complex AI architectures—including Deep Blue's rule-based logic and AlphaGo's deep reinforcement learning—applied to approachable games like Tic Tac Toe, Connect Four, and Last Coin Standing. Designed for learners, it bridges the gap between theoretical AI research and functional code.
MIT-Efficient-AI is a curated repository containing lecture notes and educational materials from MIT courses 6.S965 and 6.5940. It focuses on the intersection of TinyML and efficient deep learning, providing students and researchers with the foundational knowledge required to optimize neural networks for resource-constrained hardware. The repository serves as a valuable academic resource for understanding how to deploy high-performance AI models on edge devices, covering techniques like pruning, quantization, and efficient architecture design.
This repository by mzarnecki provides a comprehensive collection of Jupyter Notebooks focused on developing agentic AI applications. It covers the end-to-end process of building, orchestrating, and evaluating LLM-powered agents using the LangChain and LangGraph ecosystems. Designed as a practical course, it guides developers through complex agentic workflows, prompt engineering techniques, and the implementation of multi-agent systems, making it an essential resource for those looking to master modern AI application development.
The videodb-cookbook, maintained by the VideoDB team, is a comprehensive repository of Jupyter Notebooks designed to help developers integrate video data into AI workflows. It provides hands-on examples for implementing RAG (Retrieval-Augmented Generation) on video content, multimodal search, and automated video processing. By leveraging VideoDB's infrastructure, this cookbook simplifies the complexity of indexing, querying, and analyzing video streams, enabling developers to build sophisticated AI-powered video applications with minimal boilerplate code.
The IBM Granite Workshop is an open-source repository designed to help developers learn how to implement IBM's Granite AI models. Created by IBM, this collection of Jupyter Notebooks provides practical, step-by-step guidance on core AI tasks. Users can explore prompt engineering, Retrieval-Augmented Generation (RAG), text summarization, and time-series forecasting. It serves as a comprehensive resource for engineers looking to integrate enterprise-grade Granite models into their own applications, bridging the gap between theoretical knowledge and real-world deployment.
Microsoft's 'Generative AI with JavaScript' is an interactive, project-based curriculum designed for developers. It uses a unique time-traveling narrative to teach core AI concepts, including prompt engineering, RAG, and LLM integration. By meeting historical figures through code, learners gain hands-on experience with modern AI tools and frameworks, making the transition from traditional web development to AI-powered applications engaging and accessible.
SchoolOfAISaoPaulo/aulas is an open-source repository featuring a series of educational lessons from the São Paulo School of Artificial Intelligence. Created by the community and contributors, it provides practical, hands-on Jupyter Notebooks that guide learners through essential topics including linear regression, statistics, GANs, and LSTM neural networks. It serves as a valuable resource for students and practitioners looking to build a strong foundation in machine learning using Python.
Developed by Minh-Chien Trinh at Jeonbuk National University, this repository provides a structured collection of Jupyter Notebooks designed for graduate-level courses in Deep Learning and Computer Vision. It serves as a practical, hands-on resource for students and practitioners to understand the fundamental mechanics of neural networks by implementing them from the ground up without relying on high-level abstraction libraries.
RiazML/math-for-llms is an open-source educational repository providing a complete mathematical roadmap for AI practitioners. Created by RiazML, this collection of Jupyter Notebooks bridges the gap between fundamental concepts and advanced research frontiers. It covers essential topics including linear algebra, calculus, probability, and optimization, specifically tailored to help developers understand the mechanics behind modern neural networks and transformer architectures. It serves as a structured learning path for anyone looking to move beyond surface-level implementation into the core theory of deep learning.
The LUMI AI Guide is an essential resource provided by the LUMI supercomputer team to help researchers and developers migrate AI applications to high-performance computing (HPC) environments. It covers the complexities of distributed training, multi-GPU scaling, and MLOps workflows specifically optimized for the LUMI architecture. By providing practical tutorials and best practices, it bridges the gap between standard cloud-based machine learning and massive-scale supercomputing, enabling users to leverage one of the world's fastest systems for their deep learning projects.
Tour of Agents is an interactive educational resource created by ahumblenerd that provides a fast-track understanding of how AI agents function. By leveraging Pyodide to run Python code directly in the browser, the course offers a hands-on experience without complex local setups. It covers the fundamental mechanics of agentic workflows, making it an ideal starting point for developers looking to transition from basic LLM prompting to building autonomous, multi-step AI agents using popular frameworks.
Easy Data x AI is an introductory course developed by Datawhalechina designed for AI enthusiasts. It provides a structured, dual-track learning path that bridges the gap between data science and AI agent development. The curriculum focuses on practical implementation, teaching students how to leverage data-driven insights to build intelligent agents, covering essential topics like context engineering, memory management, and database integration using modern frameworks.
Created by Amirhossein Honardoust, this repository serves as an essential professional guide for navigating the trade-offs between Retrieval-Augmented Generation (RAG) and Fine-Tuning. It provides clear workflows, decision frameworks, and best practices for implementing LLM solutions. By analyzing the strengths of each approach, the guide helps practitioners determine when to use external knowledge retrieval versus internal model weight adjustment, ultimately enabling more efficient and accurate generative AI applications in real-world scenarios.
Snailclimb/AIGuide is a curated knowledge repository designed for developers navigating the AI landscape. Created by Snailclimb, this resource provides deep insights into AI application development, including practical tutorials and engineering strategies. It covers essential modern technologies such as Large Language Models (LLMs), AI Agents, Retrieval-Augmented Generation (RAG), Model Context Protocol (MCP), and advanced coding tools like Claude Code and Cursor. It serves as both a technical handbook and a preparation guide for AI-focused engineering roles.
Claude Code from Scratch is an educational project by Windy3f3f3f3f that demystifies complex AI coding agents. Instead of navigating 500,000 lines of production code, this repository provides a concise, 4,000-line implementation in Python and TypeScript. Through an 11-chapter tutorial, developers learn the fundamental architecture, tool-calling mechanisms, and orchestration logic required to build a functional coding agent from the ground up.
jinbooooom/ai-infra-hpc is an educational repository providing deep technical insights into the infrastructure powering modern AI. Created by jinbooooom, it serves as a curriculum for high-performance computing (HPC). The project covers critical low-level technologies including collective communication via MPI and NCCL, CUDA programming, SIMD vectorization, and RDMA networking. It is an essential resource for engineers looking to understand the hardware-software co-design required for training large-scale LLMs and deep learning models.
aipath is an open-source, interactive educational project created by buynao designed to demystify artificial intelligence. It provides a comprehensive curriculum consisting of 30 lessons that explain complex AI concepts without requiring advanced mathematical knowledge. By focusing on conceptual understanding and practical intuition, it serves as an accessible entry point for non-technical individuals, students, and professionals looking to grasp the fundamentals of machine learning and AI architecture in a structured, self-paced format.
Lightning-AI/dl-fundamentals is an educational repository designed to teach the core concepts of deep learning. Created by the Lightning AI team, it provides a structured series of Jupyter Notebooks and exercises that guide learners through modern machine learning workflows. By leveraging PyTorch, the project offers practical, code-first lessons that bridge the gap between theoretical understanding and real-world implementation, making it an essential resource for students and practitioners looking to solidify their foundational knowledge in the field.
Grokking Artificial Intelligence Algorithms is the official companion repository for Rishal Hurbans' book. It provides clean, educational Python implementations of fundamental AI and machine learning algorithms. Covering everything from search algorithms and evolutionary computation to neural networks and reinforcement learning, this resource is designed to help developers and students bridge the gap between theoretical concepts and practical code execution.
AI Engineering From Scratch (Chinese) is an extensive educational repository designed to guide developers through the journey of becoming AI Agent engineers. Created by fancyboi999, this project offers a structured 20-stage learning path comprising 503 lessons. It provides high-quality Chinese translations, dedicated companion websites, and animated video explanations, covering everything from foundational AI concepts to advanced agentic workflows and LLM integration.
AI-Practices is an educational repository created by zimingttkx, offering a structured series of Jupyter Notebooks for mastering machine learning and deep learning. It covers fundamental concepts and advanced architectures, including linear regression, neural networks, CNNs, and RNNs. Designed for practical learning, the repository provides clear implementations using popular frameworks like Keras, PyTorch, and Scikit-learn, making it an excellent resource for students and practitioners looking to bridge the gap between theory and real-world application.
This repository contains the official source code for the 'Mastering Python for Finance, Second Edition' book by James Ma Weiming. It serves as a practical guide for developers and financial analysts looking to implement quantitative finance models using Python. The collection features numerous Jupyter Notebooks covering essential topics such as time-series analysis, portfolio optimization, derivative pricing, and machine learning applications in financial markets, providing a hands-on approach to building robust financial systems.
