Kagenti ADK Server SDK

Python SDK for packaging agents for deployment to Kagenti ADK infrastructure.

Overview

The kagenti-adk provides Python utilities for wrapping agents built with any framework (LangChain, CrewAI, BeeAI Framework, etc.) for deployment on Kagenti ADK. It handles the A2A (Agent-to-Agent) protocol implementation, platform service integration, and runtime requirements so you can focus on agent logic.

Key Features

• Framework-Agnostic Deployment - Wrap agents from any framework for Kagenti ADK deployment
• A2A Protocol Support - Automatic handling of Agent-to-Agent communication
• Platform Service Integration - Connect to Kagenti ADK's managed LLM, embedding, file storage, and vector store services
• Context Storage - Manage data associated with conversation contexts

Installation

uv add kagenti-adk

Quickstart

import os

from a2a.types import (
    Message,
)
from a2a.utils.message import get_message_text
from kagenti_adk.server import Server
from kagenti_adk.server.context import RunContext
from kagenti_adk.a2a.types import AgentMessage

server = Server()

@server.agent()
async def example_agent(input: Message, context: RunContext):
    """Polite agent that greets the user"""
    hello_template: str = os.getenv("HELLO_TEMPLATE", "Ciao %s!")
    yield AgentMessage(text=hello_template % get_message_text(input))

def run():
    try:
        server.run(host=os.getenv("HOST", "127.0.0.1"), port=int(os.getenv("PORT", 8000)))
    except KeyboardInterrupt:
        pass


if __name__ == "__main__":
    run()

Run the agent:

uv run my_agent.py

Available Extensions

The SDK includes extension support for:

• Citations - Source attribution (CitationExtensionServer, CitationExtensionSpec)
• Trajectory - Agent decision logging (TrajectoryExtensionServer, TrajectoryExtensionSpec)
• Settings - User-configurable agent parameters (SettingsExtensionServer, SettingsExtensionSpec)
• LLM Services - Platform-managed language models (LLMServiceExtensionServer, LLMServiceExtensionSpec)
• Agent Details - Metadata and UI enhancements (AgentDetail)
• And more - See Documentation

Each extension provides both server-side handlers and A2A protocol specifications for seamless integration with Kagenti ADK's UI and infrastructure.

Resources

• Kagenti ADK Documentation
• GitHub Repository
• PyPI Package

Contributing

Contributions are welcome! Please see the Contributing Guide for details.

Support

• GitHub Issues
• GitHub Discussions

Developed by contributors to the Kagenti project, this initiative is part of the Linux Foundation AI & Data program. Its development follows open, collaborative, and community-driven practices.