My Agentic AI Experiment and Learning Project

Experiments with Gemini and xAI APIs using intelligent caching.

Prerequisites

• Python 3.9+
• uv package manager

Install uv

macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Or via Homebrew:

brew install uv

Windows:

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Quick Start

1. Clone the repository

   git clone https://github.com/TonyGregg/AgenticExperiments.git
   cd AgenticExperiments

2. Install dependencies

   # This installs all dependencies from pyproject.toml
   uv sync

3. Set up environment variables

   # Create .env file
   cp .env.example .env
   
   # Edit .env and add your API keys
   # GEMINI_API_KEY=your_gemini_key_here
   # XAI_API_KEY=your_xai_key_here

4. Run the application

   uv run python main.py

5. Run the application in server mode

uv run python run_server.py

Development

Install with dev dependencies

uv sync --all-extras

Run tests

uv run pytest

Format code

uv run black src/

Type checking

uv run mypy src/

Project Structure

my-agentic-ai/
├── src/
│   ├── agents/          # AI agent implementations
│   ├── utils/           # Utilities (cache, config)
│   ├── models/          # Data models
│   └── services/        # API clients
├── tests/               # Unit tests
├── data/                # Cache and data files (gitignored)
├── main.py              # Entry point
├── pyproject.toml       # Dependencies and project config
└── uv.lock              # Locked dependency versions

Adding New Dependencies

# Add runtime dependency
uv add package-name

# Add dev dependency
uv add --dev package-name

License

MIT