Built on GitHub’s native /mcp integration, Copilot can search issues, analyze labels and activity, and summarize scope so you can move from backlog to implementation without context hunting.
| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Download Repo ZIP] [Original HTTPS Page] |
Run a GitHub-native agent in your terminal that works directly with your issues and pull requests, executes across a /fleet of parallelized subagents, and carries you from /plan to merged code.
Read the documentation. Available with Copilot Free, Pro, Pro+, Max, Business, and Enterprise.
Use /model to switch, then /fleet to execute in parallel or run multiple models at once.
Return to long-running work and keep moving. Memory and compaction keep sessions from collapsing under their own history.
Start in the CLI with a /plan, then open the work in VS Code to refine code directly.
Compare plans and run /fleet across your preferred models to execute with parallelized subagents. Refine in your /IDE and ship your pull request on GitHub.
Built on GitHub’s native /mcp integration, Copilot can search issues, analyze labels and activity, and summarize scope so you can move from backlog to implementation without context hunting.

Shift+Tab into plan mode to outline the work, use /model to compare approaches, and then Shift+Tab into autopilot mode when you want Copilot to carry the task forward without step-by-step approval.

Use AGENTS.md and Agent Skills to define custom instructions and tool access, so behavior stays consistent across models, sessions, and delegated work.

Install Copilot CLI with npm install -g @github/copilot and run /plan on your next task.
Read the documentationLearn how to set up Copilot CLI and use the terminal for your agentic workflows.
Discover an ecosystem of partner and community-driven MCP servers to connect to Copilot CLI.
Follow a guided GitHub Skills module and create an application step by step using Copilot CLI in your terminal.
Copilot CLI access is included as part of your Copilot subscription. Each interaction with the agent draws on your respective plan’s AI Credits allowance. For additional information on billing, please refer to our documentation.
There are multiple ways to install and set up Copilot CLI. Install via npm with npm install -g @github/copilot, then authenticate using your existing GitHub credentials. The CLI automatically inherits your organization's Copilot policies and governance settings. Please see the installation guide to read options for Homebrew, WinGet, and more.
Yes. Copilot CLI works with your existing Copilot Business or Enterprise subscription — no additional billing or setup required. However, your organization's admin needs to enable Copilot CLI.
Copilot CLI supports macOS, Linux, and Windows.
Copilot CLI operates independently in your terminal and can modify files that any editor can then display, making it useful regardless of your editor choice — especially for editors that don't have official Copilot extensions.
Yes, you can interact with Copilot CLI in the VS Code integrated terminal and in the VS Code chat panel. Please see our docs page for more information.
Yes, Copilot CLI supports Model Context Protocol (MCP) server integrations, skills, and plugins, allowing you to add custom capabilities and contextual richness tailored to your unique development environment.
Copilot CLI supports models from multiple foundation model providers, such as Anthropic, Google, and OpenAI. You can switch models per task or use multiple models for the same task when needed.
Copilot CLI excels at legacy codebase navigation, new repository creation, cross-platform development setup, and multi-step implementations, and any scenario requiring autonomous task execution with terminal-native workflows.
Yes. Copilot CLI supports subagents and multi‑agent workflows. With /fleet, you can run the same task across multiple subagents in parallel and converge on one decision‑ready result, with full control over what’s applied.
Copilot CLI maintains session persistence within and across sessions, allowing you to build on previous conversations and maintain context throughout your development workflow.
Copilot CLI automatically inherits your organization's existing Copilot governance policies. It's built on GitHub's trusted platform infrastructure with the same security standards and compliance that protect millions of developers.
Every file change and command execution requires your explicit approval before being applied. You maintain complete visibility and control over all autonomous actions.
Copilot CLI access is included as part of your Copilot subscription. Each interaction with the agent draws on your respective plan’s AI Credits allowance. For additional information on billing, please refer to our documentation.
There are multiple ways to install and set up Copilot CLI. Install via npm with npm install -g @github/copilot, then authenticate using your existing GitHub credentials. The CLI automatically inherits your organization's Copilot policies and governance settings. Please see the installation guide to read options for Homebrew, WinGet, and more.
Yes. Copilot CLI works with your existing Copilot Business or Enterprise subscription — no additional billing or setup required. However, your organization's admin needs to enable Copilot CLI.
Copilot CLI supports macOS, Linux, and Windows.
Copilot CLI operates independently in your terminal and can modify files that any editor can then display, making it useful regardless of your editor choice — especially for editors that don't have official Copilot extensions.
Yes, you can interact with Copilot CLI in the VS Code integrated terminal and in the VS Code chat panel. Please see our docs page for more information.
Yes, Copilot CLI supports Model Context Protocol (MCP) server integrations, skills, and plugins, allowing you to add custom capabilities and contextual richness tailored to your unique development environment.
Copilot CLI supports models from multiple foundation model providers, such as Anthropic, Google, and OpenAI. You can switch models per task or use multiple models for the same task when needed.
Copilot CLI excels at legacy codebase navigation, new repository creation, cross-platform development setup, and multi-step implementations, and any scenario requiring autonomous task execution with terminal-native workflows.
Yes. Copilot CLI supports subagents and multi‑agent workflows. With /fleet, you can run the same task across multiple subagents in parallel and converge on one decision‑ready result, with full control over what’s applied.
Copilot CLI maintains session persistence within and across sessions, allowing you to build on previous conversations and maintain context throughout your development workflow.
Copilot CLI automatically inherits your organization's existing Copilot governance policies. It's built on GitHub's trusted platform infrastructure with the same security standards and compliance that protect millions of developers.
Every file change and command execution requires your explicit approval before being applied. You maintain complete visibility and control over all autonomous actions.
| Back | FazBrowse Home | New Git URL |