This repository curates practical AI agents and generative AI applications, showcasing real-world implementations across diverse tech stacks including OpenAI, Gemini, and local models. It targets developers and researchers seeking to understand and build with modern AI frameworks, offering a valuable resource for learning and inspiration.

How It Works

The collection is organized into five categories: Starter Agents, Advanced Agents, Multi-Agent Teams, RAG Applications, and Multimodal Apps. Each entry represents a complete, functional AI application, demonstrating specific use cases and integrations with various AI models and frameworks like LangChain and CrewAI. This structured approach facilitates exploration and adoption of different AI patterns.

Quick Start & Requirements

This repository is a collection of code examples and does not have a single installation command. Users will need to clone the repository and follow individual application instructions. Prerequisites will vary per application but commonly include Python, specific AI model API keys (OpenAI, Gemini, Anthropic), and potentially libraries like LangChain or CrewAI.

Highlighted Details

• Showcases a wide range of AI applications, from simple chatbots to complex multi-agent systems and multimodal solutions.
• Features integrations with major AI providers (OpenAI, Google Gemini, Anthropic Claude) and local models (Llama).
• Includes Retrieval-Augmented Generation (RAG) examples and multimodal applications combining text, image, audio, and video.
• Provides a development roadmap targeting over 100 applications by the end of 2025.

Maintenance & Community

The project is actively maintained with a roadmap indicating daily releases and a target of 100+ applications by the end of 2025. Discussions and suggestions for new apps or improvements are encouraged via the Issues section.

Licensing & Compatibility

This project is licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

As a curated collection, each application's complexity and dependencies vary significantly. Users must individually assess and set up each example, which may require specific hardware or API access.