A collection of 28 code-first tutorials for taking GenAI agents from prototype to production, covering memory, RAG, deployment, security and observability.
NirDiamant/GenAI_Agents
A collection of 50+ runnable Jupyter notebook tutorials covering GenAI agent techniques, from simple chatbots to multi-agent systems.
- Stars
- 24,639
- Forks
- 4,147
- Open issues
- 27
- Last commit
- 9 hours ago
What is it?
GenAI_Agents is a learning repository of tutorials and implementations for building generative AI agents. Each entry is a notebook that walks through one agent design, from a basic conversational bot with history management to multi-agent systems built with LangGraph, AutoGen, CrewAI and OpenAI Swarm.
The catalog is organized by difficulty and domain, including beginner examples, framework introductions to LangGraph and the Model Context Protocol (MCP), and applied agents for education, customer support, contract analysis, testing and content creation. Many entries link to companion explainer videos and blog posts.
The repository suits developers who want concrete, working code for agent patterns such as tool calling, state management, retrieval-augmented generation and human-in-the-loop approval, rather than only conceptual overviews.
Key features
- 01Over 50 tutorial notebooks ranging from beginner to advanced levels
- 02Covers LangGraph, LangChain, AutoGen, CrewAI and OpenAI Swarm implementations
- 03Includes an introduction to the Model Context Protocol (MCP) with server and client examples
- 04Demonstrates multi-agent collaboration, memory, and human-in-the-loop approval patterns
- 05Organized into a searchable table by category, framework and key features
Use cases
- Learning how to build a first AI agent from scratch
- Comparing agent frameworks such as LangGraph, AutoGen and CrewAI on similar tasks
- Finding a starting template for a domain-specific agent like customer support or contract review
- Studying multi-agent orchestration and tool integration patterns
Quick start
- 1
Browse the tutorial notebooks in the all_agents_tutorials folder
- 2
Open a beginner notebook such as simple_conversational_agent.ipynb and run its cells
Things to know
- The license is not clearly identified in the metadata, so check the repository's license terms before reusing the code.
Topics
FAQ
- What is GenAI_Agents?
- A collection of 50+ runnable Jupyter notebook tutorials covering GenAI agent techniques, from simple chatbots to multi-agent systems. GenAI_Agents is a learning repository of tutorials and implementations for building generative AI agents. Each entry is a notebook that walks through one agent design, from a basic conversational bot with history management to multi-agent systems built with LangGraph, AutoGen, CrewAI and OpenAI Swarm.
- Is GenAI_Agents free to use? What license does it have?
- GenAI_Agents is open source under the Other license. Check the license terms before using it in commercial products.
- Is GenAI_Agents still maintained?
- Actively maintained. The last commit to GenAI_Agents was on Oct 20, 2026.
- What can I use GenAI_Agents for?
- Learning how to build a first AI agent from scratch Comparing agent frameworks such as LangGraph, AutoGen and CrewAI on similar tasks Finding a starting template for a domain-specific agent like customer support or contract review Studying multi-agent orchestration and tool integration patterns
- How do I install GenAI_Agents?
- Browse the tutorial notebooks in the all_agents_tutorials folder Open a beginner notebook such as simple_conversational_agent.ipynb and run its cells
- Where can I get GenAI_Agents?
- The source code and installation instructions are on GitHub: https://github.com/NirDiamant/GenAI_Agents
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Python framework for building autonomous AI agents that research, plan, code and run tasks, with memory, RAG and 100+ LLM providers.
A Python library and runnable Jupyter textbook implementing 35 agentic AI architectures, from Reflexion and ReAct to MemGPT and BrowserAgent, on LangGraph.
A large collection of open-source AI agents, agent skills, and RAG apps built on Claude, Gemini, GPT, DeepSeek, Llama, and Qwen models.
A visual platform for building, testing and deploying AI agents and workflows, with built-in API and MCP server exposure.
Agent memory system that stores, recalls and reflects on memories so AI agents learn over time instead of only replaying chat history.