Skip to main content

​
Prerequisites

Before you start building with the Awesome AI Apps examples, make sure your development environment meets these requirements.

​
System Requirements

​
Python Version

All projects require Python 3.10 or higher. Many newer projects recommend Python 3.11+ for better performance and features. 
python --version
# or
python3 --version
If you have multiple Python versions installed, you may need to use python3.10 or python3.11 explicitly instead of just python.

​
Git

You’ll need Git to clone the repository: 
git --version
If you don’t have Git installed, download it from git-scm.com.

​
Package Managers

You’ll need a Python package manager to install dependencies. Choose one:

​
Option 1: pip (Standard)

pip comes bundled with Python. Verify it’s installed: 
pip --version
# or
pip3 --version
uv is a significantly faster Python package installer. We recommend using it for all projects.
1

Install uv

pip install uv
2

Verify Installation

uv --version

Why uv?

uv is 10-100x faster than pip for package installation. For projects with many dependencies, this can save significant time during setup.

​
API Keys

Most projects require API keys from various AI and service providers. Here are the most commonly used:

​
Required for Most Examples

Nebius API Key

Used in: 50+ examples across all categoriesNebius Token Factory is the primary AI inference provider used throughout this collection.Get your key:
  1. Visit Nebius Token Factory
  2. Sign up for a free account
  3. Navigate to API Keys in your dashboard
  4. Generate a new API key
Add to .env:
NEBIUS_API_KEY=your_api_key_here
Models available:
  • meta-llama/Llama-3.3-70B-Instruct
  • Qwen/Qwen3-30B-A3B
  • deepseek-ai/DeepSeek-V3-0324
  • And many more
Used in: OpenAI SDK examples, some RAG applicationsGet your key:
  1. Visit OpenAI Platform
  2. Sign up and add billing
  3. Go to API Keys section
  4. Create a new secret key
Add to .env:
OPENAI_API_KEY=sk-...

​
Project-Specific API Keys

Depending on which examples you run, you may need additional API keys:
GibsonAI Memori API KeyUsed for persistent memory in 12+ memory agent examples.
MEMORI_API_KEY=your_memori_key
Get it from: GibsonAI
Never commit API keys to version control. Always use .env files and keep them in .gitignore.

​
Environment Variable Setup

Every project includes a .env.example file showing required API keys. Here’s the standard workflow:
1

Copy the Example File

cp .env.example .env
2

Edit .env with Your Keys

Open .env in your text editor and replace placeholder values:
# .env
NEBIUS_API_KEY=your_actual_nebius_key_here
OPENAI_API_KEY=your_actual_openai_key_here
3

Verify It's Ignored by Git

The .env file should already be in .gitignore. Verify:
git status
You should NOT see .env in the list of changed files.

​
Optional Tools

​
For Streamlit Applications

Many RAG and advanced agent examples use Streamlit for web interfaces: 
pip install streamlit
Run Streamlit apps with: 
streamlit run app.py

​
For MCP Development

Model Context Protocol examples require Node.js for MCP servers: 
node --version  # Should be v16 or higher
Install from: nodejs.org

​
Code Formatting

For contributing or maintaining clean code, install formatters: 
pip install black
black .

​
Verify Your Setup

Run this checklist to ensure everything is ready:
1

Python Version

python --version  # Should be 3.10+
2

Package Manager

pip --version
# or
uv --version
3

Git

git --version
4

Clone Repository

git clone https://github.com/Arindam200/awesome-ai-apps.git
cd awesome-ai-apps
5

Test a Simple Project

cd starter_ai_agents/agno_starter
cp .env.example .env
# Edit .env with your NEBIUS_API_KEY
uv sync  # or: pip install -r requirements.txt
python main.py

​
Platform-Specific Notes

Most tools can be installed via Homebrew:
# Install Homebrew if needed
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install Python
brew install [email protected]

# Install Node.js (for MCP examples)
brew install node

​
Troubleshooting

Try using python3 instead of python. On some systems, especially Linux and macOS, the default python command points to Python 2.x.
python3 --version
python3 main.py
On Linux/macOS, avoid using sudo pip. Instead, use virtual environments or install with --user flag:
pip install --user -r requirements.txt
Better approach - use virtual environments:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
If you get SSL errors when installing packages, your system certificates might be outdated:
# macOS
/Applications/Python\ 3.11/Install\ Certificates.command

# Linux - install ca-certificates
sudo apt install ca-certificates
Ensure you’re using the same Python version for installation and execution:
# Use same Python binary
python3.11 -m pip install -r requirements.txt
python3.11 main.py

​
Next Steps

Once your environment is set up, head to the Quick Start Guide to run your first AI agent example.

Ready to Build?

Follow the quick start guide to run your first agent in under 5 minutes

Build docs developers (and LLMs) love

Get started for freeTalk to us