explaingit

arindam200/awesome-ai-apps

★ 12,188PythonAudience · developerComplexity · 3/5Setup · moderate

TLDR

A collection of 80+ ready-to-run Python code examples for building AI applications, from simple chatbots and voice assistants to multi-agent systems and apps that search your own documents, plus an 8-lesson AWS Strands course.

Mindmap

mindmap
  root((repo))
    What it does
      AI app examples
      8-lesson course
      Starter templates
    Categories
      Agents
      Voice assistants
      RAG apps
      MCP tools
    Tech
      Python
      AWS Strands SDK
    Audience
      Developers
      AI builders
    Complexity
      Starter examples
      Advanced patterns
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Copy a starter agent example to quickly build a Python chatbot that can search the web or call external APIs.

USE CASE 2

Build a retrieval-augmented generation app that answers questions using your own folder of documents.

USE CASE 3

Learn multi-agent patterns by running the course examples that show multiple AI systems working together on a task.

Tech stack

PythonAWS Strands SDK

Getting it running

Difficulty · moderate Time to first run · 30min

Most examples require API keys for LLM providers, AWS Strands examples require an AWS account with Strands SDK access.

In plain English

This repository is a curated collection of more than 80 practical code examples for building applications that use large language models (LLMs), which are AI systems trained to generate and understand text. The examples cover several categories of AI application: text-based agents, voice assistants, retrieval-augmented generation apps, and tools that connect AI to external data sources using the Model Context Protocol (MCP). Retrieval-augmented generation (RAG) is a technique where an AI looks up relevant information from a database or document set before generating a response, helping it give more accurate and specific answers. An agent is an AI system that can take actions such as searching the web, calling an API, or running code, rather than just answering questions. MCP is a protocol that lets AI systems connect to external tools and services in a standardized way. The collection is organized by complexity and type. Starter and simple agents are the quickest to run and understand, while the advanced agents section covers more involved patterns. Separate categories group voice agents (that can speak and listen), memory agents (that retain information across conversations), and RAG applications together for easier browsing. The repository also includes an 8-lesson course on building AI agents with the AWS Strands SDK. The course progresses from basic agent setup and session management through multi-agent patterns, where multiple AI agents work together, and ends with production topics like safety guardrails and observability. Most examples are written in Python. The project is aimed at developers who want working starting points for common AI application patterns rather than theory-first explanations.

Copy-paste prompts

Prompt 1
Using the starter agent examples in awesome-ai-apps, build a Python AI agent that searches the web and returns a bullet-point summary of the top results.
Prompt 2
Show me how to build a RAG app from the awesome-ai-apps examples that answers questions based on a folder of PDF files I provide.
Prompt 3
Walk me through the AWS Strands SDK course in awesome-ai-apps to create a memory agent that remembers what I told it in previous messages.
Open on GitHub → Explain another repo

← arindam200 on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.