Paul Krill
Editor at Large

GitHub Copilot SDK allows developers to build Copilot agents into apps

news
Jan 23, 20262 mins

Available in a technical preview, the SDK for Node.js, Python, Go, and .NET provides programmatic access to the agentic power of the Copilot CLI.

A human hand against a midnight-black background holds a tablet like a platter with the word "AI" resting on top. AI tools, AI technology, AI innovation.
Credit: Deemerwha studio / Shutterstock

GitHub has launched a technical preview of the GitHub Copilot SDK, a tool kit for embedding the “agentic core” of the GitHub Copilot CLI into applications.

Available on GitHub, the SDK was unveiled on January 22. Initially available for Node.js/TypeScript, Python, Go, and .NET, the GitHub Copilot SDK exposes the same engine behind the GitHub Copilot CLI, a production-tested agent runtime that can be invoked programmatically. There is no need to build orchestration, according GitHub. Users define agent behavior, and Copilot handles planning, tool invocation, file edits, and more, according to GitHub. A GitHub Copilot subscription is required to use the SDK.

Developers using the SDK can take advantage of GitHub Copilot CLI’s support for multiple AI models, custom tool definitions, Model Context Protocol (MCP) server integration, GitHub authentication, and real-time streaming. GitHub teams already have used the SDK for applications such YouTube chapter generators, custom GUIs for agents, speech-to-command workflows to run apps, games in which players can compete with AI, and ummarizing tools.

“Think of the Copilot SDK as an execution platform that lets you reuse the same agentic loop behind the Copilot CLI, while GitHub handles authentication, model management, MCP servers, custom agents, and chat sessions plus streaming,” said GitHub’s Mario Rodriguez, chief product officer for the GitHub product team and the author of the January 21 blog post. “That means you are in control of what gets built on top of those building blocks.”

Paul Krill

Paul Krill is editor at large at InfoWorld. Paul has been covering computer technology as a news and feature reporter for more than 35 years, including 30 years at InfoWorld. He has specialized in coverage of software development tools and technologies since the 1990s, and he continues to lead InfoWorld’s news coverage of software development platforms including Java and .NET and programming languages including JavaScript, TypeScript, PHP, Python, Ruby, Rust, and Go. Long trusted as a reporter who prioritizes accuracy, integrity, and the best interests of readers, Paul is sought out by technology companies and industry organizations who want to reach InfoWorld’s audience of software developers and other information technology professionals. Paul has won a “Best Technology News Coverage” award from IDG.

More from this author