GitHub Copilot in Android Studio: Setup and Project Context
GitHub Copilot works in Android Studio through a JetBrains plugin. Here is how to install it, check compatibility, run your first task, and keep project rules available for any connected assistant.
Updated 5 min read
GitHub Copilot is available in Android Studio through the official GitHub Copilot plugin for JetBrains IDEs. Once installed, it provides inline code completions, a chat panel for asking questions about your code, and suggestions as you type. Tools like fenbs complement the setup by keeping project rules, architecture decisions, and task status in a shared record that any connected assistant can read before starting work on the codebase.
Check compatibility before installing
The GitHub Copilot plugin supports Android Studio Jellyfish and later. Older versions of Android Studio are not supported. Open Android Studio > Help > About to check your current version. If you are on an older release, update Android Studio before installing Copilot. Android Studio updates are available from the Android Developers site or through the IDE's own update mechanism.
You also need a GitHub account with an active Copilot subscription or access through an organization plan. Copilot is available on individual and business plans; check your account settings on GitHub.com to confirm access before proceeding.
Install the GitHub Copilot plugin
- Open Android Studio and go to Settings (Windows/Linux) or Preferences (macOS) > Plugins.
- Click the Marketplace tab and search for "GitHub Copilot."
- Click Install on the official GitHub Copilot plugin and wait for the download to complete.
- Restart Android Studio when prompted.
- After restart, open the GitHub Copilot sign-in prompt from the bottom status bar or from Tools > GitHub Copilot > Sign In. Follow the browser flow to authorize your GitHub account.
If the plugin does not appear in the Marketplace, check that your IDE proxy settings allow connections to the JetBrains plugin repository. In corporate environments, a network proxy or firewall may block the download. Contact your IT team if the plugin cannot be downloaded directly.
Configure the plugin and check it is working
After signing in, open or create an Android project and start typing in a Kotlin or Java file. You should see gray inline suggestions appear as you type; press Tab to accept one. If no suggestions appear, check the Copilot status icon in the bottom right of the IDE. It shows whether Copilot is enabled, whether you are signed in, and whether any errors are present.
You can also open the Copilot Chat panel from the sidebar or the Tools menu. Ask it a question about a class in your project, such as "What does this class do?" or "How should I handle null safety here?" The chat panel has access to your open files and can see the code you are looking at.
First coding task with Copilot in Android Studio
A good first task is writing a unit test for an existing function. Open the function, place the cursor at the end, and start a new test class in the test directory. Copilot will suggest the structure and individual test cases. Accept the suggestions, review them, and run the tests to confirm they pass. This gives you a concrete result quickly and lets you evaluate the quality of the suggestions on real code.
Copilot's suggestions are based on the content of your open files and the public code it was trained on. It does not know your project architecture unless that information is in the files you have open. Open the relevant source files in the editor before asking Copilot a question that requires project-specific context.
When Copilot suggestions are off or low quality
Poor suggestion quality usually has one of three causes: the context Copilot can see is too limited, the file type or language is not well supported, or there is a network or authentication issue. Check the Copilot status icon first to rule out authentication problems. If suggestions are consistently unhelpful for a specific file type, check the GitHub Copilot documentation for the current list of supported languages.
For more on Copilot's available models and how to choose between them for different tasks, see GitHub Copilot models. For alternative AI coding tools, see GitHub Copilot alternatives.
Keep project rules available to every coding assistant you use
fenbs stores project architecture decisions, coding standards, and task context outside the IDE. When you switch from Copilot to another assistant, or when a colleague uses a different tool on the same codebase, the project rules are available from Integrations rather than buried in open editor tabs. Connect the assistant and it reads the project context before it starts.
Create a free accountFree for one person · No credit card · Works with Claude, ChatGPT, Cursor and more
How to do this with fenbs
- Create a free account and add a project for the Android app.
- Write the architecture decisions, naming conventions, and key technical choices as Decisions and rules. Include the Android version targets, the architecture pattern (MVVM, MVI, etc.), and any libraries that are approved or prohibited.
- Add tasks for current features, bugs, and enhancements on the kanban board. Keep each task's plan up to date as the work progresses.
- Connect a supported AI assistant from Integrations so it reads the project context before you ask it to add or change code.
- Before ending a session, ask the assistant to save progress for the tasks it touched, including what was completed and what remains.
fenbs does not connect directly to Android Studio or to GitHub Copilot. It keeps the project decisions and task state in a form that any supported AI assistant can read. For running Copilot from the command line, see GitHub Copilot CLI.
If the Copilot plugin causes unexpected behavior in Android Studio, such as conflicts with other plugins or slow completions, check the GitHub Copilot status page and the plugin's issue tracker before spending time on local debugging.