Awesome AI Apps
A curated collection of 132 example AI apps, tutorials, and recipes built with LLMs, agents, and RAG.
- Stars
- 16.7k
- Forks
- 1.9k
- Licence
- MIT
- Language
- Python
- Last update
- 6 days ago
- Type
- Curated list
What it is
This is a large collection of example projects, tutorials, and starter recipes showing how to build AI-powered applications. It covers topics such as AI agents, voice assistants, retrieval-augmented generation (RAG), and MCP-backed tools, with examples across several frameworks and stacks. People use it as a reference to see working code for common AI app patterns.
- Browse the Starter Agents section to see small examples for frameworks such as AutoGen, CrewAI, LangChain, and smolagents
- Pick a RAG or Memory Agent project as a base for your own document question-answering app
- Follow the Tutorials & Videos section to learn specific techniques
- Adapt an MCP Agent example to connect an LLM to external tools
Great for
- Developers learning how to build LLM agents with a specific framework
- Students looking for working example projects to study
- Engineers comparing how different AI frameworks handle similar tasks
- Builders who want a starting template for a RAG or voice agent app
Not ideal for
- People looking for a single polished product to use directly, since this is a collection of separate examples
- Non-developers, because most entries assume familiarity with Python and API keys
- Teams needing production-hardened code, since the README describes these as guides and starters rather than supported products
How to get it
- 1
Clone and build from source
You'll need: Git · Python
Clone the repository
git clone https://github.com/Arindam200/awesome-ai-apps - 2
Run it
- Clone the repository and open the folder for the project you want
- Read that project's own README for its setup steps and required API keys
- Install that project's dependencies as its README describes
- Run the example script or app it provides
- 3
Get the most out of it
- Start with the Starter Agents section to learn the basic pattern for each framework
- Compare the same task across frameworks, such as LangChain and LangGraph, to see the trade-offs
- Use the MCP Agents section to learn how tools are exposed to models
Downloads
Strengths
- Covers many frameworks and use cases in one place, with 132 listed projects
- Each entry links to its own folder, so you can run only the one you need
- Released under the MIT license, which allows reuse and modification
Trade-offs
- It is a directory of separate projects, so quality, dependencies, and maintenance vary between entries
- Several examples reference specific hosted model providers, which may require paid API keys
- The README shown is truncated, so this summary covers only the sections visible here
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| awesome-ai-apps (this) | 16.7k | Curated list | intermediate | 6 days ago | Developers learning how to build LLM agents with a specific framework |
| langchain | 149k | Framework | intermediate | 4 days ago | Python developers building LLM-powered applications |
| crewAI | 60.4k | Library | intermediate | 4 days ago | Python developers prototyping multi-agent workflows |
| llama_index | 52.8k | Library | intermediate | 10 days ago | Python developers building retrieval-augmented generation (RAG) apps over private documents |
| ai-engineering-from-scratch | 76.3k | Learning resource | intermediate | 4 days ago | Students who want to understand how LLMs, retrieval, and agents work internally |
| ai-engineering-hub | 40.8k | Learning resource | intermediate | 5 days ago | Developers who want working examples of RAG or agent systems to adapt |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.