Skip to main content

About GitHub Copilot

GitHub Copilot can help you code by offering autocomplete-style suggestions. You can learn what to consider while using GitHub Copilot, and how GitHub Copilot works.

About GitHub Copilot

GitHub Copilot is an AI pair programmer that offers autocomplete-style suggestions as you code. You can receive suggestions from GitHub Copilot either by starting to write the code you want to use, or by writing a natural language comment describing what you want the code to do. GitHub Copilot analyzes the context in the file you are editing, as well as related files, and offers suggestions from within your text editor. GitHub Copilot is powered by OpenAI Codex, a new AI system created by OpenAI.

GitHub Copilot is trained on all languages that appear in public repositories. For each language, the quality of suggestions you receive may depend on the volume and diversity of training data for that language. For example, JavaScript is well-represented in public repositories and is one of GitHub Copilot's best supported languages. Languages with less representation in public repositories may produce fewer or less robust suggestions.

GitHub Copilot is available as an extension in Visual Studio Code, Visual Studio, Neovim and the JetBrains suite of IDEs. For more information, see "Getting started with GitHub Copilot."

Using GitHub Copilot

You can see real-world examples of GitHub Copilot in action. For more information, see the GitHub Copilot website.

GitHub Copilot offers suggestions from a model that OpenAI built from billions of lines of open source code. As a result, the training set for GitHub Copilot may contain insecure coding patterns, bugs, or references to outdated APIs or idioms. When GitHub Copilot produces suggestions based on this training data, those suggestions may also contain undesirable patterns.

You are responsible for ensuring the security and quality of your code. We recommend you take the same precautions when using code generated by GitHub Copilot that you would when using any code you didn't write yourself. These precautions include rigorous testing, IP scanning, and tracking for security vulnerabilities. GitHub provides a number of features to help you monitor and improve code quality, such as GitHub Actions, Dependabot, CodeQL and code scanning. All these features are free to use in public repositories. For more information, see "Understanding GitHub Actions" and "GitHub security features."

GitHub Copilot uses filters to block offensive words in the prompts and avoid producing suggestions in sensitive contexts. We are committed to constantly improving the filter system to more intelligently detect and remove offensive suggestions generated by GitHub Copilot, including biased, discriminatory, or abusive outputs. If you see an offensive suggestion generated by GitHub Copilot, please report the suggestion directly to copilot-safety@github.com so that we can improve our safeguards.

Managed user accounts cannot use GitHub Copilot.

About billing for GitHub Copilot

GitHub Copilot is a paid feature, requiring a monthly or yearly subscription. Verified students, teachers, and maintainers of popular open source projects on GitHub are eligible to use GitHub Copilot for free. If you meet the criteria for a free GitHub Copilot subscription, you will be automatically notified when you visit the GitHub Copilot subscription page. If you do not meet the criteria for a free GitHub Copilot subscription, you will be offered a 60 day free trial, after which a paid subscription is required for continued use. For more information, see "About billing for GitHub Copilot."

About the license for the GitHub Copilot plugin in JetBrains IDEs

GitHub, Inc. is the licensor of the JetBrains plugin. The end user license agreement for this plugin is the GitHub Terms for Additional Products and Features and use of this plugin is subject to those terms. JetBrains has no responsibility or liability in connection with the plugin or such agreement. By using the plugin, you agree to the foregoing terms.

Further reading