A curated repository of 126 practical projects, tutorials, and recipes for building LLM-powered applications across multiple AI frameworks. Developers must be prepared to write or execute code and configure external API keys, as most projects depend on remote LLM providers and may incur variable usage costs.
Project overview
It provides a large, curated variety of examples spanning from starter snippets to advanced pipelines, covering diverse frameworks such as LangChain, CrewAI, AutoGen, and LlamaIndex.
Project type
MCP · AI Agent · RAG
Use cases
Documents & Office · Knowledge Q&A
Deployment
Refer to project documentation
License
MIT
Best for
Developers and AI engineers who are willing to write or execute code and want practical examples for building LLM-powered applications across various frameworks.
Key capabilities
Quick-start agents designed for learning and extending different AI frameworks.
Straightforward, practical use-cases for everyday AI applications.
Examples for building real-time voice assistants and streaming speech pipelines.
Examples using Model Context Protocol for external tool integration.
Agents with advanced memory capabilities for context retention and personalization.
Retrieval-augmented generation examples for document understanding and knowledge bases.
Complex multi-agent pipelines for production-ready end-to-end workflows.
End-to-end examples of fine-tuning open-source LLMs, covering data preparation through deployment.
Limitations and risks
Most projects require external API keys to function, necessitating the use of remote LLM model providers.
Using the required external APIs may incur variable usage costs depending on the model provider.
Getting started
Clone the repository, select a specific project directory, configure required environment variables such as API keys, install dependencies, and run the project. This process has a medium difficulty due to manual dependency management and code execution.
Alternatives and comparisons
An open-source .NET framework providing modular components and plug-ins for building AI bots and managing multi-agent scenarios.
A Go-native stack providing LLM agents, graph workflows, tool calling, memory, and evaluation for production-grade agent systems.
A lightweight Java AI application development framework organizing LLM calls, tool calling, agents, and RAG into clear modules.
GitHub project description: A collection of projects showcasing RAG, agents, workflows, and other AI use cases
README: This repository is a comprehensive collection of **126 practical projects, tutorials, and recipes** for building powerful LLM-powered applications, including text agents, voice as…
README: **Quick-start agents for learning and extending different AI frameworks.** _20 projects_
README: **Straightforward, practical use-cases for everyday AI applications.** _18 projects_
README: **Real-time voice assistants and streaming speech pipelines.** _8 projects_