patchy631/ai-engineering-hub
AI Engineering Hub offers in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for all skill levels.
Awesome MCP › MCP Resources & Educational Materials
the-ai-merge/multimodal-agents-course
The project "Kubrick Course" is an open-source educational course designed to teach developers how to build advanced AI agents capable of understanding and processing multimodal data including images, text, audio, and video. It focuses on the Model Context Protocol (MCP) to create a multimodal AI agent named Kubrick AI, which is specialized in video processing tasks. The course is a collaboration between The Neural Maze, Neural Bits, Pixeltable, and Opik, aiming to provide a hands-on, production-ready approach to building AI systems beyond basic tutorials. The course covers building an MCP server for video processing using Pixeltable and FastMCP, designing a custom Groq-powered agent connected to the MCP server, and integrating the system with Opik for observability and prompt versioning. It teaches how to use Pixeltable for multimodal data processing, create complex MCP servers exposing resources, prompts, and tools, and implement custom MCP clients and tool agents using LLMs like Llama 4 Scout and Maverick. Participants will learn to build a multimodal processing pipeline, a video search engine exposed to an agent via MCP, and a production-ready API to power the agent. The course emphasizes LLMOps principles, software engineering best practices, and covers topics such as video embeddings, streaming APIs, and Vision Language Models (VLMs). It is designed for ML/AI engineers, software engineers, and data scientists interested in building complex AI systems that integrate multiple data modalities. The course is beginner to intermediate level, with prerequisites including basic programming and AI/ML concepts. It is free and open-source, supported by sponsors Pixeltable and Opik, and uses freemium plans from OpenAI and Groq for model inference. The syllabus includes modules on multimodal AI concepts, MCP server building, agent implementation, and system design, with detailed guides, video lessons, and code examples. Overall, this project is a comprehensive educational resource for developers aiming to master MCP-based multimodal AI agents, focusing on practical implementation and real-world applications in video and multimodal data processing.
https://github.com/the-ai-merge/multimodal-agents-course
Also in MCP Resources & Educational Materials
NirDiamant/GenAI_Agents
This repository offers a comprehensive collection of over 50 tutorials and implementations for Generative AI Agent techniques, ranging from basic conversational bots to complex multi-agent systems,...
NirDiamant/agents-towards-production
This repository offers end-to-end, code-first tutorials for building and deploying production-grade Generative AI agents, scaling from prototype to enterprise.
microsoft/mcp-for-beginners
An open-source curriculum designed to teach the concepts and fundamentals of the Model Context Protocol (MCP) with practical coding examples in multiple programming languages.
Arindam200/awesome-ai-apps
A comprehensive collection of practical examples, tutorials, and tools for building powerful LLM-powered AI applications, including chatbots, agents, and workflows, with a focus on the Model Context Protocol (MCP).
modelcontextprotocol/modelcontextprotocol
The Model Context Protocol project provides a standardized specification and schema for managing model context to enable interoperability in model-driven systems.
heilcheng/awesome-agent-skills
A curated repository of modular skills, tools, and tutorials for enhancing AI coding agents like Claude, Codex, Copilot, and VS Code through dynamic instruction files.
ashishps1/learn-ai-engineering
A comprehensive curated collection of free resources to learn AI, Machine Learning, Large Language Models, AI Agents, and the Model Context Protocol from scratch.