GitHub Copilot transforms the developer experience. Backed by the leaders in AIGitHub Copilot provides contextualized assistance throughout the software development lifecyclefrom inline suggestions and chat assistance in the IDE to code explanations and answers to docs in GitHub and more. With GitHub Copilot elevating their workflowdevelopers can focus on: valueinnovationand happiness.

GitHub Copilot enables developers to focus more energy on problem solving and collaboration and spend less effort on the mundane and boilerplate. That’s why developers who use GitHub Copilot report up to 75% higher satisfaction with their jobs than those who don’t and are up to 55% more productive at writing code without sacrifice to qualitywhich all adds up to engaged developers shipping great software faster.

GitHub Copilot integrates with leading editorsincluding Visual Studio CodeVisual StudioJetBrains IDEsand Neovimandunlike other AI coding assistantsis natively built into GitHub. Growing to millions of individual users and tens of thousands of business customersGitHub Copilot is the world’s most widely adopted AI developer tool and the competitive advantage developers ask for by name.

GitHub Copilot Free is a new free pricing tier with limited functionality for individual developers. Users assigned a Copilot Business or Copilot Enterprise seat are not eligible for access. Users with access to Copilot Pro through a paid subscriptiontrialor through an existing verified OSSstudentfacultyor MVP account may elect to use Free instead. 

GitHub Copilot is trained on all languages that appear in public repositories. For each languagethe quality of suggestions you receive may depend on the volume and diversity of training data for that language. For exampleJavaScript 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 CodeVisual StudioVimNeovimthe JetBrains suite of IDEsand Azure Data Studio. Although inline suggestion functionality is available across all these extensionschat functionality is currently available only in Visual Studio CodeJetBrainsand Visual Studio. GitHub Copilot is also supported in terminals through GitHub CLI and as a chat integration in Windows Terminal Canary. With the GitHub Copilot Enterprise planGitHub Copilot is natively integrated into GitHub.com. All plans are supported in GitHub Copilot in GitHub Mobile. GitHub Mobile for Copilot Pro and Copilot Business have access to Bing and public repository code search. Copilot Enterprise in GitHub Mobile gives you additional access to your organization's knowledge.

NoGitHub Copilot generates suggestions using probabilistic determination.

• When thinking about intellectual property and open source issuesit is critical to understand how GitHub Copilot really works. The AI models that create GitHub Copilot’s suggestions may be trained on public codebut do not contain any code. When they generate a suggestionthey are not “copying and pasting” from any codebase.

• To generate a code suggestionthe GitHub Copilot extension begins by examining the code in your editor—focusing on the lines just before and after your cursorbut also information including other files open in your editor and the URLs of repositories or file paths to identify relevant context. That information is sent to GitHub Copilot’s modelto make a probabilistic determination of what is likely to come next and generate suggestions.

• To generate a suggestion for chat in the code editorthe GitHub Copilot extension creates a contextual prompt by combining your prompt with additional context including the code file open in your active documentyour code selectionand general workspace informationsuch as frameworkslanguagesand dependencies. That information is sent to GitHub Copilot’s modelto make a probabilistic determination of what is likely to come next and generate suggestions.

• To generate a suggestion for chat on GitHub.comsuch as providing an answer to a question from your chat promptGitHub Copilot creates a contextual prompt by combining your prompt with additional context including previous promptsthe open pages on GitHub.com as well as retrieved context from your codebase or Bing search. That information is sent to GitHub Copilot’s modelto make a probabilistic determination of what is likely to come next and generate suggestions. 

GitHub Copilot has multiple offerings for organizations and an offering for individual developers. All the offerings include both inline suggestion and chat assistance. The primary differences between the organization offerings and the individual offering are license managementpolicy managementand IP indemnity.

Organizations can choose between GitHub Copilot Business and GitHub Copilot Enterprise. GitHub Copilot Business primarily features GitHub Copilot in the coding environment - that is the IDECLI and GitHub Mobile. GitHub Copilot Enterprise includes everything in GitHub Copilot Business. It also  adds an additional layer of customization for organizations and integrates into GitHub.com as a chat interface to allow developers to converse with GitHub Copilot throughout the platform. GitHub Copilot Enterprise can index an organization’s codebase for a deeper understanding of the customer’s knowledge for more tailored suggestions and will offer customers access to fine-tuned customprivate models for inline suggestions.

GitHub Copilot Individual is designed for individual developersfreelancersstudentseducatorsand open source maintainers. The plan includes all the features of GitHub Copilot Business except organizational license managementpolicy managementand IP indemnity.

GitHub Copilot is powered by generative AI models developed by GitHubOpenAIand Microsoft. It has been trained on natural language text and source code from publicly available sourcesincluding code in public repositories on GitHub.

GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in codeand is included in GitHub Advanced Security.

GitHub Copilot is entirely optional and requires you to opt in before gaining access. You can easily configure its usage directly in the editorenabling or disabling it at any time. Additionallyyou have control over which file types GitHub Copilot is active for.

Access to Copilot Business and Enterprise is managed by your GitHub Administrator. They can control access to preview featuresmodelsand set GitHub Copilot policies for your organization. Additionallyyou can use your network firewall to explicitly allow access to Copilot Business and/or block access to Copilot Pro or Free. For more detailsrefer to the documentation.

GitHub Copilot has multiple offerings for organizations and an offering for individual developers. All the offerings include both code completion and chat assistance. The primary differences between the organization offerings and the individual offering are license managementpolicy managementand IP indemnity.

Organizations can choose between GitHub Copilot Business and GitHub Copilot Enterprise. GitHub Copilot Business primarily features GitHub Copilot in the coding environment - that is the IDECLI and GitHub Mobile. GitHub Copilot Enterprise includes everything in GitHub Copilot Business. It also  adds an additional layer of customization for organizations and integrates into GitHub.com as a chat interface to allow developers to converse with Copilot  throughout the platform. GitHub Copilot Enterprise can index an organization’s codebase for a deeper understanding of the customer’s knowledge for more tailored suggestions and will offer customers access to fine-tuned customprivate models for code completion.

GitHub Copilot Pro is designed for individual developersfreelancersstudentseducatorsand open source maintainers. The plan includes all the features of GitHub Copilot Business except organizational license managementpolicy managementand IP indemnity.

If you're on the Free planyou can upgrade to Pro through your Copilot settings page or directly on the Copilot marketing page.

GitHub Copilot Free users are limited to 2000 completions and 50 chat requests (including Copilot Edits).

GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in codeand is included in GitHub Advanced Security and available to all public repositories.

Organizations can now enable Copilot code review on all pull requests on github.com—including pull requests from users who are not assigned a Copilot license.

This allows you to extend the quality and rich analysis of Copilot code review to all pull requestsregardless of its authorgiving you complete coverage and confidence that pull requests have been reviewed.

To enable this functionalityan enterprise/org admin must first have Copilot enabled and then enabled two policies.

Note: This capability is not supported for Copilot code reviews in VS Code or other IDEs.

Usage from non-licensed users is billed directly to your organization as "premium requests" (PRUs) at the standard multiplier rate for Copilot code review. This flexible model allows you to get full review coverage on every PR without needing to purchase a full Copilot seat for non-development contributors who may not need Copilot. Usage from your existing licensed users simply continues to draw from their included monthly allowance as it does today.

No. This capability is off by default and gives the enterprise admin control to enable or disable. An admin must explicitly enable two separate policies to activate: 

1. ‘Premium request paid usage’ must be enabled to allow enterprises to be charged for premium requests exceeding their included usage.

2. A new Copilot code review policy (‘Allow members without a Copilot license to use Copilot code review in github.com’) must also be enabled.

We encourage admins to set up budgets to control spending on our metered productsespecially customers who have not enabled the ‘Premium request paid usage’ policy in the past. You can track all premium request usage in your billing dashboard to monitor and control spending.

GitHub Copilot processes personal data based on how Copilot is accessed and used: whether via GitHub.commobile appextensionsor one of various IDE extensionsor through features like suggestions for the command line interface (CLI)IDE code completionsor personalized chat on GitHub.com. The types of personal data processed may include:

• User Engagement Data: This includes pseudonymous identifiers captured on user interactions with Copilotsuch as accepted or dismissed completionserror messagessystem logsand product usage metrics. 

• Prompts: These are inputs for chat or codealong with contextsent to Copilot's AI to generate suggestions. 

• Suggestions: These are the AI-generated code lines or chat responses provided to users based on their prompts. 

• Feedback Data: This comprises real-time user feedbackincluding reactions (e.g.thumbs up/down) and optional commentsalong with feedback from support tickets.

No. GitHub does not use either Copilot Business or Enterprise data to train its models. 

How GitHub uses Copilot data depends on how the user accesses Copilot and for what purpose. Users can access GitHub Copilot through the webextensionsmobile appscomputer terminaland various IDEs (Integrated Development Environments). GitHub generally uses personal data to:

• Delivermaintainand update the services as per the customer's configuration and usageto ensure personalized experiences and recommendations

• Troubleshootwhich involves preventingdetectingresolvingand mitigating issuesincluding security incidents and product-related problemsby fixing software bugs and maintaining the online services' functionality and up-to-dateness

• Enhance user productivityreliabilityeffectivenessqualityprivacyaccessibilityand security by keeping the service current and operational

These practices are outlined in GitHub’s Data Protection Agreement (DPA)which details our data handling commitments to our data controller customers. 

GitHub also uses certain personal data with customer authorization under the DPAfor the following purposes:

• Billing and account management

• To comply with and resolve legal obligations 

• For abuse detectionpreventionand protectionvirus scanningand scanning to detect violations of terms of service

• To generate summary reports for calculating employee commissions and partner incentives

• To produce aggregated reports for internal use and strategic planningcovering areas like forecastingrevenue analysiscapacity planningand product strategy,

For details on GitHub's data processing activities as a controllerparticularly for Copilot Pro customersrefer to the GitHub Privacy Statement.

If and for how long GitHub’s retains Copilot data depends on how a Copilot user accesses Copilot and for what purpose. The default settings for Copilot Business and Enterprise Customers are as follows: 

Access through IDE for Chat and Code Completions:

• Prompts and Suggestions: Not retained

• User Engagement Data: Kept for two years.

• Feedback Data: Stored for as long as needed for its intended purpose.

All other GitHub Copilot access and use:

• Prompts and Suggestions: Retained for 28 days.

• User Engagement Data: Kept for two years.

• Feedback Data: Stored for as long as needed for its intended purpose.

Retaining prompts and suggestions is necessary for chat on github.commobileand CLI Copilot because those features’ effectiveness depends on using thread history to improve responses. The Copilot model requires access to previous interactions to deliver accurate and relevant suggestions. 

Yes. GitHub and customers can enter a Data Protection Agreement that supports compliance with the GDPR and similar legislation.

While we've designed GitHub Copilot with privacy in mindthe expansive definition of personal data under legislation like the EU’s General Data Protection Regulation (GDPR) means we can't guarantee it will never output such data. The Large Language Model (LLM) powering GitHub Copilot was trained on public code and there were instances in our tests where the tool made suggestions resembling personal data. These suggestions were typically synthesized and not tied to real individuals. 

These actions are available to Copilot users as described in the GitHub Privacy Statement.

The primary IP considerations for GitHub Copilot relate to copyright. The model that powers Copilot is trained on a broad collection of publicly accessible codewhich may include copyrighted codeand Copilot’s suggestions (in rare instances) may resemble the code its model was trained on. Here’s some basic information you should know about these considerations:

Copyright law permits the use of copyrighted works to train AI models:  Countries around the world have provisions in their copyright laws that enable machines to learnunderstandextract patternsand facts from copyrighted materialsincluding software code. For examplethe European UnionJapanand Singaporehave express provisions permitting machine learning to develop AI models. Other countries including CanadaIndiaand the United States also permit such training under their fair use/fair dealing provisions. GitHub Copilot’s AI model was trained with the use of code from GitHub’s public repositories—which are publicly accessible and within the scope of permissible copyright use.

What about copyright risk in suggestions? In rare instances (less than 1% based on GitHub’s research)suggestions from GitHub may match examples of code used to train GitHub’s AI model. AgainCopilot does not “look up” or “copy and paste” codebut is instead using context from a user’s workspace to synthesize and generate a suggestion.

Our experience shows that matching suggestions are most likely to occur in two situations: (i) when there is little or no context in the code editor for Copilot’s model to synthesizeor (ii) when a matching suggestion represents a common approach or method. If a code suggestion matches existing codethere is risk that using that suggestion could trigger claims of copyright infringementwhich would depend on the amount and nature of code usedand the context of how the code is used. In many waysthis is the same risk that arises when using any code that a developer does not originatesuch as copying code from an online sourceor reusing code from a library. That is why responsible organizations and developers recommend that users employ code scanning policies to identify and evaluate potential matching code.

In Copilotyou can opt whether to allow Copilot to suggest code completions that match publicly available code on GitHub.com. For more informationsee "Configuring GitHub Copilot settings on GitHub.com". If you have allowed suggestions that match public codeGitHub Copilot can provide you with details about the matching code when you accept such suggestions. Matching code does not necessarily mean copyright infringementso it is ultimately up to the user to determine whether to use the suggestionand what and who to attribute (along with other license compliance) in appropriate circumstances.

YesGitHub Copilot does include an optional code referencing filter to detect and suppress certain suggestions that match public code on GitHub.

• GitHub has created a duplication detection filter to detect and suppress suggestions that contain code segments over a certain length that match public code on GitHub. This filter can be enabled by the administrator for your enterprise and it can apply for all organizations within your enterpriseor the administrator can defer control to individual organizations. 

• With the filter enabledCopilot checks code suggestions for matches or near-matches against public code on GitHub of 65 lexemes or more (on average,150 characters). If there is a matchthe suggestion will not be shown to the user.

• In addition to off-topicharmfuland offensive output filtersGitHub Copilot also scans the outputs for vulnerable code.

YesGitHub Copilot is previewing a code referencing feature as an additional tool to assist users to find and review potentially relevant open source licenses. Code referencing is currently available in Visual Studio Code. This feature searches across public GitHub repositories for code that matches a Copilot suggestion. If there’s a matchusers will find its information displayed in the Copilot console logincluding where the match occurredany applicable licensesand a deep link to learn more. The deep link will take users to a navigable page on GitHub.com to browse examples of the code match and their repository licensesand see how many repositories—including ones without licenses—that code appears inas well as links to those repositories. Copilot users can review this information to determine whether the applicable suggestions are suitable for useand whether additional measures may be necessary to use them.

We don’t determine whether a suggestion is capable of being ownedbut we are clear that GitHub does not claim ownership of a suggestion. Whether a suggestion generated by an AI model can be owned depends on many factors (e.g. the intellectual property law in the relevant countrythe length of the suggestionthe extent that suggestion is considered ‘functional’ instead of expressiveetc).

• If a suggestion is capable of being ownedour terms are clear: GitHub does not claim ownership.

• GitHub does not claim ownership of any suggestion. In certain casesit is possible for Copilot to produce similar suggestions to different users. For exampletwo unrelated users both starting new files to code the quicksort algorithm in Java will likely get the same suggestion. The possibility of providing similar suggestions to multiple users is a common part of generative AI systems.

Public code may contain insecure coding patternsbugsor references to outdated APIs or idioms. When GitHub Copilot synthesizes code suggestions based on this datait can also synthesize code that contains these undesirable patterns. Copilot has filters in place that either block or notify users of insecure code patterns that are detected in Copilot suggestions. These filters target the most common vulnerable coding patternsincluding hardcoded credentialsSQL injectionsand path injections. Additionallyin recent years we’ve provided tools such as GitHub Advanced SecurityGitHub ActionsDependabotand CodeQL to open source projects to help improve code quality. Of courseyou should always use GitHub Copilot together with good testing and code review practices and security toolsas well as your own judgment.

No. Copilot is a tool intended to make developers more efficient. It’s not intended to replace developerswho should continue to apply the same sorts of safeguards and diligence they would apply with regard to any third-party code of unknown origin.

• The product is called “Copilot” not “Autopilot” and it’s not intended to generate code without oversight. You should use exactly the same sorts of safeguards and diligence with Copilot’s suggestions as you would use with any third-party code.

• Identifying best practices for use of third party code is beyond the scope of this section. That saidwhatever practices your organization currently uses – rigorous functionality testingcode scanningsecurity testingetc. – you should continue these policies with Copilot’s suggestions. Moreoveryou should make sure your code editor or editor does not automatically compile or run generated code before you review it.

Not necessarily. GitHub Copilot users should align their use of Copilot with their respective risk tolerances.

• As noted aboveGitHub Copilot is not intended to replace developersor their individual skill and judgmentand is not intended to fully automate the process of code development. The same risks that apply to the use of any third-party code apply to the use of Copilot’s suggestions.

• Depending on your particular use caseyou should consider implementing the protections discussed above. It is your responsibility to assess what is appropriate for the situation and implement appropriate safeguards.

• You’re entitled to IP indemnification from GitHub for the unmodified suggestions when Copilot’s filtering is enabled. If you do elect to enable this featurethe copyright responsibility is oursnot our customers. As part of our ongoing commitment to responsible AIGitHub and Microsoft extends our IP indemnity and protection support to our customers who are empowering their teams with GitHub Copilot. See Microsoft's Copilot Copyright Commitment for more details.

We are conducting internal testing of GitHub Copilot’s ease of use by developers with disabilities and working to ensure that GitHub Copilot is accessible to all developers. Please feel free to share your feedback on GitHub Copilot accessibility in our feedback forum.

GitHub Copilot includes filters to block offensive language in the prompts and to avoid synthesizing suggestions in sensitive contexts. We continue to work on improving the filter system to more intelligently detect and remove offensive outputs. If you see offensive outputsplease report them directly to [email protected] so that we can improve our safeguards. GitHub takes this challenge very seriously and we are committed to addressing it.

Given public sources are predominantly in EnglishGitHub Copilot will likely work less well in scenarios where natural language prompts provided by the developer are not in English and/or are grammatically incorrect. Thereforenon-English speakers might experience a lower quality of service.

GitHub Copilot is powered by generative AI models developed by GitHubOpenAIand Microsoft. It has been trained on natural language text and source code from publicly available sourcesincluding code in public repositories on GitHub.

1. Data from June 2023. Additional research can be found here.

2. Feature in public beta for Copilot Pro and Business plans. Requires use of repositoriesissuesdiscussionsActionsand other features of GitHub.

3. Authentication with SAML single sign-on (SSO) available for organizations using GitHub Enterprise Cloud.