Back to services

GitHub Copilot CLI

GitHub Copilot CLI is GitHub's AI coding agent for the terminal. It can read, write, and run code from the command line. It connects directly to GitHub issues and pull requests, and can take you all the way from planning to merging your code.

View alternatives to GitHub Copilot CLI
Contributor:
einverne
Suggest edit
Recent reviews

Alternatives

Tech stack

No tech stack added yet. Sign in to suggest some

GitHub Copilot CLI is a GitHub-native AI agent that runs in your terminal. It can read, write, and run code and work directly with issues and pull requests, so you can go from planning a task to committing code without leaving your shell.

Key features

  • Plan-to-PR workflow: Use /plan to work through a task first, then carry out the implementation and finally open a pull request on GitHub.
  • Parallel subagents: /fleet lets multiple subagents work on the same task in parallel and combines their output into a single result you can base decisions on.
  • Multi-model switching: Use /model to switch models, with support for models from Anthropic, Google, OpenAI, and other providers. You can also have several models work on the same task and compare the results.
  • Plan and Autopilot modes: Press Shift+Tab to enter plan mode and map out the work. When you want Copilot to proceed on its own without confirming each step, switch to autopilot mode.
  • Native GitHub MCP integration: Search issues, analyze labels and activity, and summarize the scope of a task, moving straight from your backlog to implementation.
  • Extensible and customizable: Supports MCP servers, Skills, and plugins. You can use AGENTS.md and Agent Skills to define custom instructions and tool permissions, keeping behavior consistent across different models, sessions, and delegated tasks.
  • Session persistence: /resume lets you pick up where you left off. Memory and compaction mechanisms keep long sessions from being weighed down by their history.
  • Works with your IDE: Start with /plan in the CLI, then refine the code in VS Code. You can also use Copilot CLI in VS Code's integrated terminal and chat panel.

Who it's for and use cases

It suits developers who are comfortable working in the terminal, users whose editors don't officially support the Copilot extension, and teams already using GitHub issue and PR workflows. According to the official documentation, it is especially good at navigating legacy codebases, creating new repositories, setting up cross-platform development environments, and multi-step implementations, and it also fits any scenario that calls for terminal-native, autonomous task execution.

Security and governance

  • Every file change and command execution takes effect only after you explicitly approve it.
  • It automatically inherits the Copilot governance policies already set by your organization.
  • For users on Copilot Business or Enterprise, an organization administrator must enable Copilot CLI first.

Installation and requirements

  • Supports macOS, Linux, and Windows.
  • Install with npm: npm install -g @github/copilot.
  • Or install with a script: curl -fsSL https://gh.io/copilot-install | bash.
  • The official installation docs also cover other methods such as Homebrew and WinGet.
  • After installation, sign in with your existing GitHub account.

Pricing

Copilot CLI is included in the Copilot Free, Pro, Pro+, Max, Business, and Enterprise plans at no additional cost. Each interaction with the agent consumes AI Credits from your plan's allowance. See the official documentation for the specific billing rules.