This guide will help you set up the Google ADK (Agent Development Kit) with Agent OS integration using uv for fast and reliable dependency management.

• Python 3.9 or higher
• uv - Fast Python package installer and resolver

git clone https://github.com/google/adk-python.git
cd adk-python

uv venv

# On Linux/macOS
source .venv/bin/activate

# On Windows
.venv\Scripts\activate

uv pip install -e .

This will install the ADK package in editable mode along with all required dependencies including:

• Google GenAI SDK
• LiteLLM for multi-provider LLM support
• FastAPI for web services
• And many more...

adk run ./contributing/samples/agent_os

This will start an interactive CLI with the Agent OS Agent that includes:

• Agent OS workflows and tools
• Spec-driven development capabilities
• Product planning and documentation features
• Code generation with Agent OS standards

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

For development with additional tools:

uv pip install -e ".[dev,test]"

The contributing/samples/ directory contains several examples:

• agent_os/ - Agent OS integration with full workflow support
• core_basic_config/ - Basic agent configuration
• multi_agent_basic_config/ - Multi-agent setup
• workflow_agent_seq/ - Sequential workflow agents

1. Permission Errors: Make sure you have write permissions in the project directory
2. Python Version: Ensure you're using Python 3.9 or higher
3. uv Not Found: Install uv using curl -LsSf https://astral.sh/uv/install.sh | sh

• Check the documentation
• Review the examples
• Open an issue on GitHub

After installation, you can:

1. Explore Examples: Try different sample configurations
2. Create Your Own Agent: Use the Agent OS workflows for your projects
3. Integrate with Services: Connect to various LLM providers via LiteLLM
4. Deploy: Use the deployment tools for production environments

Happy coding! 🚀