This project demonstrates how to build and run AI Agents using the Agent Development Kit (ADK), integrated with Google's Gemini models.
-
Clone the Repository
git clone https://github.com/Tsaihemanth150/ai-agents-with-adk.git cd ai-agents-with-adk -
(Optional) Create a Virtual Environment
python -m venv venv source venv/bin/activate # Linux/macOS .\venv\Scripts\activate # Windows
-
Install Requirements
pip install -r requirements.txt
- Visit: https://makersuite.google.com/app/apikey
- Generate a new API key.
- Create a
.envfile in the root of the project and add:GEMINI_API_KEY=your_api_key_here
-
Start ADK Web (if using Genkit ADK)
npx genkit dev
Make sure you have Genkit installed:
npm install -g @genkit-ai/cli -
Run the Agent Code
python src/agent_main.py
Replace
agent_main.pywith your actual entry‑point file if different.
ai-agents-with-adk/
│
├── .env # Environment variables
├── requirements.txt # Python dependencies
├── src/ # Agent logic
│ └── agent_main.py # Main script
├── prompts/ # Prompt templates (if used)
├── README.md # This file
└── ...
- Modular Agent Architecture
- Gemini‑powered AI responses
- ADK web for managing and testing agents
- Double‑check that your
.envfile exists and contains the correctGEMINI_API_KEY. - If you see module import errors, ensure you activated the virtual environment.
- Use
--forcewith pip install if needed:pip install --force-reinstall -r requirements.txt
MIT — free to use, modify, and distribute.
Built by @Tsaihemanth150