GitHub Introduces Copilot CLI for Terminal-Based AI Coding Assistance

Sep 28, 2025
GitHub has launched the Copilot CLI in public preview, bringing AI-powered coding assistance directly to the terminal. This tool allows developers to interact with an AI agent for coding tasks using natural language.

GitHub has launched the Copilot CLI in public preview, bringing the power of its AI coding assistant directly to the terminal. According to the GitHub blog, this new tool allows developers to interact with an AI agent for coding tasks using natural language, without the need for context switching.

The Copilot CLI integrates seamlessly with GitHub, enabling users to access repositories, issues, and pull requests directly from the command line. It supports terminal-native development, allowing developers to build, edit, debug, and refactor code with the help of an AI collaborator. This tool is designed to work with existing GitHub accounts and supports authentication via personal access tokens.

Installation is straightforward, requiring Node.js v22 or higher and npm v10 or higher. Developers can install the CLI globally using npm and authenticate with their GitHub account to start using it. The CLI supports both Claude Sonnet 4 and GPT-5 models, providing flexibility in AI model usage.

GitHub Copilot CLI is available for Linux, macOS, and Windows (experimental), and requires an active Copilot subscription. As this is an early-stage preview, GitHub encourages users to provide feedback to help improve the tool.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief or AI Programming Weekly.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.