PromptsApr 6, 2026·3 min read

Awesome LLM Apps — 50+ AI App Recipes with Source Code

Curated collection of 50+ production-ready AI application examples with full source code. RAG chatbots, AI agents, multi-model apps, and more. Each recipe is a complete, runnable project. 6,000+ stars.

TL;DR
A curated collection of 50+ runnable AI app examples covering RAG chatbots, agents, and multi-model architectures.
§01

What it is

Awesome LLM Apps is a curated collection of 50+ production-ready AI application examples, each with complete source code. Every recipe is a runnable project covering categories like RAG chatbots, AI agents, multi-model apps, and more. The repository serves as a learning resource and starting point for building your own AI applications.

It is designed for developers who learn best from working code and want to skip the boilerplate when building AI applications.

§02

How it saves time or tokens

The token estimate for this workflow is 2,800 tokens. Instead of building AI applications from scratch, you clone a recipe that matches your use case and modify it. Each recipe includes dependency management, environment setup, and working integration code, saving hours of initial setup and debugging.

§03

How to use

  1. Browse the collection on GitHub
  2. Clone the repository: git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
  3. Navigate to your chosen recipe: cd awesome-llm-apps/<recipe-name>
  4. Install dependencies and run: pip install -r requirements.txt && python app.py
§04

Example

# Clone the collection
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps

# Example: Run a RAG chatbot recipe
cd rag-chatbot
pip install -r requirements.txt

# Set your API key
export OPENAI_API_KEY=sk-your-key

# Run the app
python app.py

Each recipe has its own README with specific setup instructions and configuration options.

§05

Related on TokRepo

§06

Common pitfalls

  • Each recipe has its own dependencies; installing everything globally can cause version conflicts -- use virtual environments
  • API keys are required for most recipes; check each recipe's README for which providers you need
  • Some recipes use older library versions; you may need to update dependencies for compatibility with current APIs

Frequently Asked Questions

What types of AI apps are included?+

The collection covers RAG chatbots, AI agents, multi-model applications, document Q and A systems, code assistants, and more. Each category contains multiple recipes with different approaches and model providers.

Do I need paid API keys to run the recipes?+

Most recipes require API keys from providers like OpenAI, Anthropic, or Google. Some recipes work with free-tier API access. Check each recipe's README for specific requirements.

Can I use these recipes in production?+

The recipes are designed as starting points and learning resources. They work as-is for prototyping but would need additional error handling, authentication, rate limiting, and monitoring for production deployment.

What programming languages are used?+

The recipes are primarily written in Python, using popular AI frameworks like LangChain, LlamaIndex, Streamlit, and direct provider SDKs.

How often is the collection updated?+

The repository is actively maintained with new recipes added regularly. Check the commit history and release notes for the latest additions.

Citations (3)
🙏

Source & Thanks

Created by Shubham Saboo. Licensed under MIT.

awesome-llm-apps — ⭐ 6,000+

Thanks for turning "how do I build this AI app?" into "clone and run."

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.