Kai (Konveyor AI)

<!-- trunk-ignore-begin --> <div align="center"> <a href="https://github.com/konveyor/kai"> <img src="docs/images/kai_logo.png" alt="KAI Logo" width="200" height="200"> </a> </div> <!-- trunk-ignore-end --> <br>

Kai (/kaɪ/, rhymes with pie) - An AI-enabled tool that simplifies the process of modernizing application source code to a new platform. It uses Large Language Models (LLMs) guided by static code analysis, along with data from Konveyor.

Looking for the Kai IDE extension? Head to the editor-extensions repository for installation, configuration, usage instructions, and releases.

This repository contains the backend components and documentation that support the IDE extension.

For End Users

Install the Kai IDE extension from the editor-extensions releases page and follow the extension README for setup and usage.

Migration scenarios and walkthroughs are available in the docs/scenarios/ directory.

For Developers

See CONTRIBUTING.md for development setup, coding standards, and how to submit pull requests.

Repository Components

• kai_mcp_solution_server/ - MCP (Model Context Protocol) solution server for storing and retrieving solved migration examples. Self-contained Python project with its own pyproject.toml. See its README for details.

• kai_analyzer_rpc/ - Go-based analyzer RPC plugin that serves code analysis over RPC, used by the IDE extension.

Conference Talks and Blog Posts

• 2025 April 01: Project Lightning Talk: Revolutionizing Legacy Migrations with Konveyor AI - Jonah Sussman
• 2024 November 22: Konveyor AI: supporting application modernization
• 2024 August 29: Incident Storage in Kai - A Deep Dive
• 2024 July 23: Embracing the Future of Application Modernization with KAI
• 2024 May 07: Apply generative AI to app modernization with Konveyor AI

Contributing

Our project welcomes contributions from any member of our community. To get started contributing, please see our Contributor Guide.

Code of Conduct

Refer to Konveyor's Code of Conduct here.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.