Welcome to GitHub Copilot CLI for Beginners! In this series (available in video format and on the GitHub Blog), we’ll explore how to use your AI coding assistant directly in your terminal, along with tips and tricks on how to navigate the command line like a pro!

In this blog, we’ll walk through what GitHub Copilot CLI is, how it works, and how to get started. You’ll learn how to install it using npm, authenticate with your GitHub account, grant folder permissions, and run your first prompts to generate code directly from the terminal.

Let’s get started!

What is GitHub Copilot CLI?

The GitHub Copilot CLI brings Copilot’s agentic AI capabilities right into the command-line interface (CLI), becoming like any terminal or console based tool you use (with the full context of your repos)!

What makes agents so special is their ability to perform tasks like building code and running tests autonomously, so you can build iteratively. They can even self-correct and fix errors without needing a human to prompt them.

This means you can assign tasks to Copilot, focus on other to-do list items, and then review the results and request additional changes from the terminal—all without having to interrupt your workflow or switch tools. (You can even delegate tasks to Copilot Cloud agent from inside the CLI, more on this later.)

Installing Copilot CLI

Not surprisingly, the first step to using Copilot CLI is installation. The core cross-platform way—if you already have node—to do this is via npm, using:

npm install -g @github/copilot 

If you’re using a package manager like WinGet or Homebrew, you can install Copilot CLI through those tools as well. (You’ll want to consult those tools’ documentation for the exact specifics on how to do this.)

Getting started with GitHub Copilot CLI

Once you install the product, you can launch it by typing “Copilot” in your command line. There are numerous switches you can use, which we’ll cover later in the series.

If it’s your first time in the terminal, you’ll need to log in with your GitHub credentials.

/login

This will:

• Tie the client to your Copilot account.
• Connect the readonly GitHub MCP server, which grants access to resources on GitHub. (Don’t worry, we’ll cover MCP later in the series as well!)

When using Copilot, you need to grant access to the folder for Copilot to be able to explore and potentially modify files. You can do this for only this session or save this setting to apply to later sessions, too. This will allow you to launch Copilot again in the future, without having to keep approving it for the same project.

Once you’ve done that, you can start talking to Copilot, asking it questions, and request code or other tasks.

Use cases: What you can do with Copilot CLI

Here are just a few GitHub Copilot CLI use cases. (There are many more covered in the GitHub Copilot CLI 101 blog!)

Ask for an overview of the project: Copilot will explore, open important files, and report back with its findings.

Give me an overview of this project 

Ask for code, such as a new endpoint: Copilot will look at the project, find existing documentation and examples, and try to follow the practices it sees. Again, it will ask for permission to create the file.

Let’s add a new endpoint to return all categories

Delegate tasks to Copilot cloud agent: For well-defined tasks, you can delegate to Copilot cloud agent right from the CLI. Copilot will preserve the context from your current session, create a new branch, open a draft pull request, and make the requested changes in the background before requesting your review.

/delegate Let’s deal with issue #14 to add the rest of the CRUD endpoints to games

Of course, one of the best ways to explore what you can do with Copilot CLI is to simply ask Copilot. It can look through its own documentation and provide guidance on the best ways to interact with it and explore.

Tune in for the next lesson in the series which covers using two different modes: interactive mode to have GitHub Copilot run your project locally or non-interactive mode with the -p flag for quick summaries without leaving your shell context.

Take this with you

Bringing agentic AI right to your terminal opens a whole new way to learn, experiment, and get things done without ever breaking your flow. Keep an eye out for more videos in the GitHub Copilot CLI for Beginners series, where we’ll learn about:

• Interactive vs non-interactive modes
• Copilot CLI slash commands
• Using MCP servers with Copilot CLI
• And more!

Happy coding!

More resources to explore:

• GitHub Copilot CLI for Beginners video series
• GitHub Copilot CLI 101: How to use GitHub Copilot from the command line
• Best practices for GitHub Copilot CLI

The post GitHub Copilot CLI for Beginners: Getting started with GitHub Copilot CLI appeared first on The GitHub Blog.

Links from the show

One of the best ways to get value from the Microsoft 365 Community Conference isn’t just attending sessions, it’s helping shape what gets built next.

The Research sessions at Microsoft 365 Community Conference give attendees a rare, behind-the-scenes chance to collaborate directly with the Microsoft teams designing the products millions of people use every day. These sessions are designed for customers, practitioners, and IT professionals who want their real-world experiences to influence what’s coming next across Microsoft 365.

What to Expect

These aren’t traditional lectures or breakouts. Research sessions are small-group, interactive conversations designed to bring your voice into the product design process.

In a typical session, you can expect:

• Spending dedicated time with Microsoft researchers (and sometimes partner team members)
• Discuss scenarios drawn from real customer workflows
• Review early ideas or prototypes and share what would (or wouldn’t) work in your environment
• Offer candid feedback to help prioritize and refine future experiences

Topics That Matter to You

The Research sessions focus on some of the most widely used and fast-evolving Microsoft 365 experiences, including:

• SharePoint
• OneDrive
• Microsoft Teams
• Microsoft Planner
• Microsoft Lists
• Viva Engage

Whether you’re managing these tools at scale, supporting adoption, or building solutions on top of them, your perspective helps teams understand what’s working today and what needs to change next.

How to Participate

Research sessions are invite-only to keep the groups small and ensure everyone has time to contribute.

Here’s how it works:

• Registered conference attendees will receive an email invitation to sign up for Research sessions.
• The invitation includes short descriptions of each session and a brief signup form so you can indicate which topics you’re interested in.
• Participants are required to complete a consent form and a non-disclosure agreement. Participation in Research sessions is optional. Completing the survey does not affect your ability to attend the conference if you choose not to participate.
• Spots are filled first-come, first-served, so early registration is encouraged.

Be Part of What’s Next

The Microsoft 365 Community Conference is all about learning, connection, and community—and the Research sessions take that mission one step further. This is your opportunity to go beyond listening and actively contribute to the evolution of Microsoft 365.

If you’ve ever wanted to influence the tools you rely on every day, the Research sessions are one of the most meaningful ways to do it. Keep an eye out for the invitation, choose a session that matches your interests, and bring your real-world experience to the table.

--

Attendees of the research sessions must be registered attendees of the Microsoft 365 Community Conference.

Early momentum. Clear direction. 

The Launch path highlights student founders who are at an earlier stage but already showing strong signals in how they are approaching what they are building. 

L-Guard Ltd. stood out for how clearly the problem was defined, how intentionally the solution is taking shape, and the direction it is heading next. 

As the Top Launch Startup, L-Guard Ltd. receives $50,000 USD along with continued visibility and support from Microsoft as they move their solution forward. 

Meet the startup 

L-Guard Ltd.: AI-powered road safety, built for real-time response 

Rwanda 

L-Guard Ltd. is addressing a critical gap in road safety across Africa, where many accident victims lose their lives not from the crash itself, but from delayed emergency response. 

The startup has built an AI- and IoT-powered system that monitors vehicle activity, detects crashes in real time, and automatically alerts nearby hospitals and emergency responders. By combining sensor data with machine learning models on Azure, L-Guard transforms real-time vehicle signals into actionable emergency intelligence. 

This shifts road safety from reactive response to proactive intervention, issuing risky driving warnings, detecting incidents as they happen, and ensuring that help is activated as quickly as possible, even in low-connectivity environments. 

As the startup continues to move from pilot validation toward broader deployment, the focus is on strengthening reliability, expanding partnerships, and scaling across high-risk transport markets. By making timely rescue the standard, L-Guard is working to reduce preventable fatalities and bring more accountability to emergency response systems. 

Helen Ugoeze Okereke – Growing up in Ebonyi State, Nigeria, Helen set out to become what she called a “computer wizard,” focused on building real solutions with technology. Today, she leads L-Guard’s vision and strategy, driven by a mission to use technology to save lives. 

Ramadhani Wanjenja – With a background in embedded systems and intelligent hardware, Ramadhani leads the technical architecture of L-Guard. His personal experience surviving a motorcycle accident shaped the direction of the solution and its focus on immediate response. 

Terry Manzi – Raised in Kigali, Terry brings a systems and operations mindset, leading software-hardware integration, deployment, and partnerships to ensure L-Guard works effectively in real environments. 

Erioluwa Olowoyo – With a focus on product design and user experience, Erioluwa ensures L-Guard remains intuitive and accessible. His path into technology was self-driven, shaped by a commitment to building solutions that work for real users in real contexts. 

What this represents 

The Top Launch startup reflects what it means to build with intention from the start. 

This is not about having everything finished. It is about identifying a real problem, building toward a solution, and continuing to move forward with clarity and purpose. 

As L-Guard Ltd. continues to develop, their work highlights the impact student founders can have when they combine technical skill with lived experience and a clear mission. 

Partner tools behind the build 

Alongside mentorship and community, Imagine Cup startups gain access to tools that support how their solutions continue to take shape. 

Through GitHub Education, teams use the Student Developer Pack, collaborate with AI-assisted coding through Copilot, and build on a platform used by developers around the world. 

With Replit, teams build, test, and deploy using natural language in an AI-powered environment designed for rapid iteration. 

Together, these tools give startups the flexibility and support to keep moving forward as they scale their solutions.