Version: 0.5.1

Quick Start

Build and run your first AI agent with Agent Kernel in under 5 minutes!

Requirements

Python Version: 3.12 - 3.13.x (Python 3.14+ support to be available soon)
Cloud Platforms: AWS, Azure (multi-cloud support)

Choose Your Framework

Agent Kernel supports multiple frameworks. Pick the one you're most comfortable with:

OpenAI Agents
CrewAI
LangGraph
Google ADK
Smolagents

OpenAI Agents Quick Start

1. Install

pip install agentkernel[openai]

2. Create Your Agent

Create a file called my_agent.py:

from agents import Agent as OpenAIAgent
from agentkernel.cli import CLI
from agentkernel.openai import OpenAIModule

# Define your agent
general_agent = OpenAIAgent(
    name="general",
    handoff_description="Agent for general questions",
    instructions="You provide assistance with general queries. Give short and direct answers.",
)

math_agent = OpenAIAgent(
    name="math",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning.",
)

# Register agents with Agent Kernel
OpenAIModule([general_agent, math_agent])

if __name__ == "__main__":
    CLI.main()

3. Set API Key

export OPENAI_API_KEY=your-api-key-here

4. Run Your Agent

python my_agent.py

CrewAI Quick Start

1. Install

pip install agentkernel[crewai]

2. Create Your Agent

Create a file called my_agent.py:

from crewai import Agent as CrewAgent
from agentkernel.cli import CLI
from agentkernel.crewai import CrewAIModule

# Define your agents
general_agent = CrewAgent(
    role="general",
    goal="Agent for general questions",
    backstory="You provide assistance with general queries. Give direct and short answers",
    verbose=False,
)

math_agent = CrewAgent(
    role="math",
    goal="Specialist agent for math questions",
    backstory="You provide help with math problems. Explain your reasoning at each step.",
    verbose=False,
)

# Register agents with Agent Kernel
CrewAIModule([general_agent, math_agent])

if __name__ == "__main__":
    CLI.main()

3. Set API Key

export OPENAI_API_KEY=your-api-key-here

4. Run Your Agent

python my_agent.py

LangGraph Quick Start

1. Install

pip install agentkernel[langgraph]

2. Create Your Agent

Create a file called my_agent.py:

from typing import TypedDict
from langgraph.graph import StateGraph, END
from agentkernel.cli import CLI
from agentkernel.langgraph import LangGraphModule

# Define state
class State(TypedDict):
    messages: list
    
# Define nodes
def respond(state: State):
    # Your agent logic here
    messages = state["messages"]
    response = f"Processed: {messages[-1]}"
    return {"messages": messages + [response]}

# Build graph
workflow = StateGraph(State)
workflow.add_node("agent", respond)
workflow.set_entry_point("agent")
workflow.add_edge("agent", END)

# Compile graph
graph = workflow.compile()
graph.name = "assistant"

# Register with Agent Kernel
LangGraphModule([graph])

if __name__ == "__main__":
    CLI.main()

3. Set API Key

export OPENAI_API_KEY=your-api-key-here

4. Run Your Agent

python my_agent.py

Google ADK Quick Start

1. Install

pip install agentkernel[adk]

2. Create Your Agent

Create a file called my_agent.py:

from adk import Agent as ADKAgent
from agentkernel.cli import CLI
from agentkernel.adk import GoogleADKModule

# Define your agent
agent = ADKAgent(
    name="assistant",
    model="gemini-2.0-flash-exp",
    instructions="You are a helpful AI assistant. Provide clear and concise answers.",
)

# Register with Agent Kernel
GoogleADKModule([agent])

if __name__ == "__main__":
    CLI.main()

3. Set API Key

export GOOGLE_API_KEY=your-api-key-here

4. Run Your Agent

python my_agent.py

Smolagents Quick Start

1. Install

pip install agentkernel[smolagents]

2. Create Your Agent

Create a file called my_agent.py:

from smolagents import LiteLLMModel, ToolCallingAgent
from agentkernel.cli import CLI
from agentkernel.smolagents import SmolagentsModule

model = LiteLLMModel(model_id="openai/gpt-4o")

assistant = ToolCallingAgent(
    tools=[],
    model=model,
    name="assistant",
    description="You are a helpful AI assistant. Provide concise and accurate answers.",
)

# Register with Agent Kernel
SmolagentsModule([assistant])

if __name__ == "__main__":
    CLI.main()

3. Set API Key

export OPENAI_API_KEY=your-api-key-here

4. Run Your Agent

python my_agent.py

Testing Your Agent

Once your agent is running, you'll see an interactive CLI:

(kernel) >> Using in-memory session store
AgentKernel CLI (type !help for commands or !quit to exit):
(kernel) >> No agent was requested. Defaulting to first agent in the list
(kernel) >> Selected agent: triage
(kernel) >> Starting new session: 07ec500e-f103-4b0e-8ecb-d794232f5992
(triage) >>
(triage) >> !list
Available agents:
  triage
  math
  general

(triage) >> !select math
(math) >> What is 2 + 2?

[math agent responds]
(math) >> 2 + 2 = 4. This is basic addition where we combine two quantities...

(math) >>

Understanding the Structure

Every Agent Kernel application follows this pattern:

Define agents using your preferred framework
Wrap them in an Agent Kernel Module
Run them using Agent Kernel's execution modes (CLI, API, AWS, etc.)

Next Steps

Add Custom Tools

Enhance your agent with custom tools:

from crewai import Agent, Tool

def search_database(query: str) -> str:
    # Your custom logic
    return f"Results for: {query}"

search_tool = Tool(
    name="search",
    description="Search the database",
    func=search_database
)

agent = Agent(
    role="researcher",
    goal="Find information",
    backstory="You are a research assistant",
    tools=[search_tool],
    verbose=False
)

Deploy as REST API

Run your agent as a REST API server:

# Install API dependencies
pip install agentkernel[api]

Use the RESTAPI module run the agents

from agents import Agent as OpenAIAgent
from agentkernel.api import RESTAPI
from agentkernel.openai import OpenAIModule

# Define your agent
general_agent = OpenAIAgent(
    name="general",
    handoff_description="Agent for general questions",
    instructions="You provide assistance with general queries. Give short and direct answers.",
)

math_agent = OpenAIAgent(
    name="math",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning.",
)

# Register agents with Agent Kernel
OpenAIModule([general_agent, math_agent])

if __name__ == "__main__":
    RESTAPI.run()

Run the agents

# Run as API server
python my_agent.py

Configure the API port by editing config.yaml

api:
    port: 8000

Test it:

curl -X POST http://localhost:8000/api/v1/chat \
  -H "Content-Type: application/json" \
  -d '{"agent": "general", "prompt": "Hello!"}'

Deploy to AWS Lambda

Package and deploy to AWS Lambda:

# Install AWS dependencies
pip install agentkernel[aws]

Use the Lambda module to run the agents

from agents import Agent
from agentkernel.aws import Lambda
from agentkernel.openai import OpenAIModule

math_agent = Agent(
    name="math",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your \
        reasoning at each step and include examples. \
        If prompted for anything else you refuse to answer.",
)

history_agent = Agent(
    name="history",
    handoff_description="Specialist agent for historical questions",
    instructions="You provide assistance with historical queries. \
        Explain important events and context clearly.",
)

triage_agent = Agent(
    name="triage",
    instructions="You determine which agent to use based on the user's question.",
    handoffs=[history_agent, math_agent],
)

OpenAIModule([triage_agent, math_agent, history_agent])

handler = Lambda.handler

# Deploy requires AWS credentials configured
# Terraform module imported and configured (see examples)
terraform init
terraform apply

Configure Memory

Use in-memory storage (default):

export AK_SESSION__TYPE=in_memory

Or add Redis-backed memory for persistent sessions:

export AK_SESSION__TYPE=redis
export AK_SESSION__REDIS__URL=redis://localhost:6379

Or add DynamoDB-backed memory for persisted sessions:

export AK_SESSION__TYPE=dynamodb
export AK_SESSION__DYNAMODB__TABLE_NAME=agent-kernel-sessions

See session configuration for more details.

Common Patterns

Session Management

# Sessions automatically track conversation history
# Each user/conversation gets a unique session ID
# Configure via environment variables:
# AK_SESSION_STORAGE=redis
# AK_REDIS_URL=redis://localhost:6379

Examples Gallery

Explore more examples in our Examples section:

Example snippets can be found here.

Troubleshooting

Agent Not Found

Make sure you're using the correct agent name when running:

# Agent names come from the framework-specific naming
# OpenAI: agent.name
# CrewAI: agent.role
# LangGraph: graph.name

API Key Errors

Ensure your API key is set correctly:

# OpenAI (for OpenAI, CrewAI, LangGraph)
export OPENAI_API_KEY=sk-...

# Google (for ADK)
export GOOGLE_API_KEY=...

Import Errors

Install the correct extras package:

pip install agentkernel[your-framework]

Learn More

Core Concepts - Deep dive into Agent Kernel architecture
Framework Integration - Framework-specific guides
Deployment Guide - Production deployment options
API Reference - Complete API documentation

Need help? Check out our GitHub Issues or open a discussion!

Choose Your Framework​

OpenAI Agents Quick Start​

1. Install​

2. Create Your Agent​

3. Set API Key​

4. Run Your Agent​

CrewAI Quick Start​

1. Install​

2. Create Your Agent​

3. Set API Key​

4. Run Your Agent​

LangGraph Quick Start​

1. Install​

2. Create Your Agent​

3. Set API Key​

4. Run Your Agent​

Google ADK Quick Start​

1. Install​

2. Create Your Agent​

3. Set API Key​

4. Run Your Agent​

Smolagents Quick Start​

1. Install​

2. Create Your Agent​

3. Set API Key​

4. Run Your Agent​

Testing Your Agent​

Understanding the Structure​

Next Steps​

Add Custom Tools​

Deploy as REST API​

Deploy to AWS Lambda​

Configure Memory​

Common Patterns​

Session Management​

Examples Gallery​

Troubleshooting​

Agent Not Found​

API Key Errors​

Import Errors​

Learn More​

Ready to Ship YourFirst Agent?

Choose Your Framework

OpenAI Agents Quick Start

1. Install

2. Create Your Agent

3. Set API Key

4. Run Your Agent

CrewAI Quick Start

1. Install

2. Create Your Agent

3. Set API Key

4. Run Your Agent

LangGraph Quick Start

1. Install

2. Create Your Agent

3. Set API Key

4. Run Your Agent

Google ADK Quick Start

1. Install

2. Create Your Agent

3. Set API Key

4. Run Your Agent

Smolagents Quick Start

1. Install

2. Create Your Agent

3. Set API Key

4. Run Your Agent

Testing Your Agent

Understanding the Structure

Next Steps

Add Custom Tools

Deploy as REST API

Deploy to AWS Lambda

Configure Memory

Common Patterns

Session Management

Examples Gallery

Troubleshooting

Agent Not Found

API Key Errors

Import Errors

Learn More

Ready to Ship Your
First Agent?