GitHub Copilot CLI icon

GitHub Copilot CLI

GitHub Copilot CLI is a terminal-native interface to the Copilot coding agent. It runs locally, understands your repository and GitHub context, and can plan and execute tasks such as making code changes, running commands with approval gates, committing, and opening or managing pull requests. It supports interactive chat and programmatic one-shot prompts, MCP-powered extensibility, and model selection via an environment variable. Copilot CLI is currently in public preview and available on Linux, macOS, and Windows (WSL or experimental PowerShell).

GitHub Copilot CLI - 1
GitHub Copilot CLI - 2

No discussions yet

Be the first to start a discussion about GitHub Copilot CLI

Developer

GitHub is a Microsoft-owned platform for software development and version control using Git, offering tools like Copilot, CLI, and coll…read more

Pricing and Plans

(Subscription)

Free

Free

Limited access to GitHub Copilot CLI with basic features

  • 50 agent mode or chat requests per month
  • 2,000 completions per month
  • Access to Claude Sonnet 3.5, GPT-4.1, and more

Pro

$10/month

Unlimited completions and chats with access to more models

  • Everything in Free
  • Unlimited agent mode and chats with GPT-5 mini
  • Unlimited code completions
  • Access to code review, Claude Sonnet 4, GPT-5, Gemini 2.5 Pro, and more
  • 6x more premium requests than Copilot Free
  • Coding agent

Pro+

$39/month

Maximum flexibility and model choice

  • Everything in Pro
  • Access to all models, including Claude Opus 4.1, o3, and more
  • 30x more premium requests than Copilot Free
  • Access to GitHub Spark

Pro Trial

30 days

30-day free trial of GitHub Copilot Pro

  • Full access to Pro features
  • No credit card required
  • Automatically converts to paid subscription after trial

System Requirements

Operating System
Linux, macOS, Windows (WSL or experimental PowerShell)
Memory (RAM)
2 GB+
Processor
Any modern CPU capable of running Node.js v22+
Disk Space
≈200 MB for CLI (plus Node.js runtime)

AI Capabilities

Repo-aware code understanding
Natural language to code edits
Command execution with safety approvals
Pull request creation and management
Task planning and multi-step execution
MCP extensibility for custom tools
Model switching (e.g., GPT-5 via env var)