Skip to main content
Version: 0.2.0

Installation

Get started with Agent Kernel in just a few minutes.

Prerequisites​

Before installing Agent Kernel, ensure you have:

  • Python 3.12 or higher installed on your system
  • pip or uv package manager
  • (Optional) Virtual environment tool like venv or conda

Basic Installation​

Install Agent Kernel using pip:

pip install agentkernel

This installs the core Agent Kernel library with minimal dependencies.

Framework-Specific Installation​

Agent Kernel supports multiple AI agent frameworks. Install the extras for the framework(s) you plan to use:

OpenAI Agents​

pip install agentkernel[openai]

CrewAI​

pip install agentkernel[crewai]

LangGraph​

pip install agentkernel[langgraph]

Google ADK​

pip install agentkernel[adk]

Multiple Frameworks​

You can install support for multiple frameworks at once:

pip install agentkernel[openai,crewai,langgraph]

Additional Components​

REST API Server​

For running agents with REST API endpoints:

pip install agentkernel[api]

AWS Deployment​

For deploying to AWS Lambda or ECS:

pip install agentkernel[aws]

CLI Testing​

For interactive command-line testing:

pip install agentkernel[cli]

All Features​

Install everything:

pip install agentkernel[openai,crewai,langgraph,adk,api,aws,cli]

Using UV Package Manager​

UV is a fast Python package installer. If you're using UV:

uv pip install agentkernel[openai,crewai,langgraph,api]

Virtual Environment Setup​

We recommend using a virtual environment to avoid dependency conflicts:

Using venv​

# Create virtual environment
python -m venv .venv

# Activate (Linux/macOS)
source .venv/bin/activate

# Activate (Windows)
.venv\Scripts\activate

# Install Agent Kernel
pip install agentkernel[openai,api]

Using conda​

# Create conda environment
conda create -n .venv python=3.12

# Activate
conda activate .venv

# Install Agent Kernel
pip install agentkernel[openai,api]

Verify Installation​

After installation, verify that Agent Kernel is installed correctly:

python -c "import agentkernel; print(agentkernel.__version__)"

You should see the version number printed (e.g., 0.1.2).

Development Installation​

If you want to contribute to Agent Kernel or modify the source code:

# Clone the repository
git clone https://github.com/yaalalabs/agent-kernel.git
cd agent-kernel/ak-py

# Install in development mode
./build.sh

# Go to any example and run
./build.sh local

Configuration​

Agent Kernel can be configured using environment variables or a configuration file. See the Configuration Guide for details.

Basic Environment Variables​

# Set log level
export AK_LOG_LEVEL=INFO

# Set session storage
export AK_SESSION_STORAGE=redis
export AK_REDIS_URL=redis://localhost:6379

Troubleshooting​

Python Version Issues​

Agent Kernel requires Python 3.12+. Check your Python version:

python --version

If you have multiple Python versions, use python3.12 explicitly:

python3.12 -m pip install agentkernel

Dependency Conflicts​

If you encounter dependency conflicts, try creating a fresh virtual environment:

python -m venv fresh-env
source fresh-env/bin/activate  # or fresh-env\Scripts\activate on Windows
pip install --upgrade pip
pip install agentkernel[your-extras]

Import Errors​

If you get import errors after installation, ensure you've installed the appropriate extras:

# If using OpenAI Agents
pip install agentkernel[openai]

# If using CrewAI
pip install agentkernel[crewai]

Next Steps​

Now that you have Agent Kernel installed, proceed to the Quick Start Guide to build your first agent!

Version Information​

  • Python Requirements: 3.12+
  • License: MIT

Support​

If you encounter installation issues:

  1. Check the GitHub Issues
  2. Search for existing solutions
  3. Open a new issue with your error details

Ready to build? Continue to the Quick Start Guide →