Awesome AI Agents › Courses and Tutorials
This repository is the code and syllabus for a free course on building multimodal agents, produced jointly by The Neural Maze and Neural Bits. Rather than connecting an existing MCP server to a desktop client, the course has learners build the whole system, called Kubrick: an agent that ingests video and answers questions about it. The material is organised around several components. A multimodal processing pipeline built on Pixeltable handles video, audio, image and text, produces embeddings and backs a video search engine. That search engine is exposed through an MCP server written with FastMCP which publishes tools, resources and prompts, so prompt definitions are versioned on the server side instead of living in the agent code. A custom MCP client is implemented from scratch and connected to an agent that uses Llama 4 Scout and Maverick served by Groq, with a tool-calling loop written by hand rather than taken from a framework. The system is fronted by a production-style API with streaming, and Opik provides observability, custom tracing and prompt versioning across the stack. Modules cover video handling, embeddings, streaming APIs and vision language models along with the LLMOps practices that hold the pieces together, and a companion video course walks through the same path. Prerequisites are modest: Python knowledge is required, while familiarity with LLMs, MCP and agents is described as helpful but not necessary. Setup instructions live in a separate getting started document and rely mostly on hosted model APIs so a normal laptop suffices. The intended audience is machine learning and software engineers who want a worked end-to-end example of an agent that reasons over non-text data.
https://github.com/the-ai-merge/multimodal-agents-course
A comprehensive guide and resource hub for prompt engineering, context engineering, retrieval-augmented generation, and AI agents, offering tutorials, papers, tools, and courses to optimize the use of large language models.
Learn Claude Code is an educational project that teaches how to build modern AI coding agents like Claude Code through a progressive tutorial covering core concepts, planning, subagents, and skills mechanisms.
AI Engineering Hub is a comprehensive repository offering in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for learners and practitioners.
The Hugging Face Agents Course is a comprehensive educational resource that teaches the fundamentals and advanced concepts of AI agents and large language models through structured units, practical frameworks, and community collaboration.
GenAI_Agents is a comprehensive repository offering tutorials, implementations, and community resources for building and advancing generative AI agents from basic to advanced levels.
This course provides a comprehensive project-based tutorial on Harness Engineering for building reliable AI coding agents, covering environment setup, state management, verification, and control.
An AI-powered tool that analyzes GitHub repositories and generates beginner-friendly tutorials with visualizations to simplify understanding complex codebases.
A comprehensive guide to prepare for machine learning and AI technical interviews at major tech companies, covering coding, ML fundamentals, system design, and behavioral aspects.