GitHub Copilot app launches as desktop home for AI coding agents
GitHub introduced the Copilot app, a desktop application built for working with AI coding agents, at Microsoft Build 2026. The release expands GitHub’s Copilot product line beyond editor integrations and command-line tools into a dedicated workspace for directing several agents at once.
The Copilot app is available in technical preview to existing Copilot Pro, Pro+, Business, and Enterprise subscribers.
A control center for parallel agent sessions
The Copilot app provides a single “My Work” view showing active sessions, open issues, pull requests, and background automations across connected repositories.
“Every session runs in its own git worktree, a real, isolated copy of your branch. This helps parallel agent sessions work without stepping on each other. The app handles every worktree for you: no manual setup, no cleanup, no branch juggling. Whether you start from a prompt or an issue from your inbox, Copilot gets the context it needs from existing issues, pull requests, and the repos you’ve connected,” Mario Rodriguez, Chief Product Officer at GitHub, explained.
A feature called Agent Merge follows a pull request through review and integration. It monitors continuous integration checks, tracks required reviewers, addresses failing checks, and waits for merge conditions to be met. Developers decide which steps Copilot is allowed to perform, including driving CI back to green, addressing reviewer feedback, and completing the merge.
Copilot Max, a higher-tier subscription aimed at heavy agent users, is available as an upgrade from Copilot Pro, Pro+, and EDU plans.
Canvases for inspectable work
The Copilot app also introduces canvases, work surfaces shared between humans and agents. A canvas can display a plan, pull request, browser session, terminal, deployment, dashboard, or workflow state. Agents update the canvas as work progresses, and developers can edit, reorder, approve, or redirect that work on the same surface. The chat interface handles instruction and discussion, and canvases hold the work itself for inspection and verification.
Code review updates
Copilot code review gained a medium tier that routes pull requests to a higher-reasoning model for better precision and recall. Administrators can set the review effort level for individual repositories to “low” or “medium,” matching model strength to repository risk and impact.
Two skills accompany the update. The /security-review skill provides a dedicated path for security-focused evaluation. The /rubberduck skill, now generally available, uses multiple model families to critique implementations and surface novel issues.
Copilot code review is also available natively on Azure DevOps, with the same one-click review, inline comments, and committable fix suggestions provided on GitHub. Administrators can enable it on selected repositories.
SDK, CLI, and partner integrations
The GitHub Copilot SDK reached general availability in Node.js/TypeScript, Python, Go, .NET, Rust, and Java. The SDK exposes the same agentic runtime that powers the Copilot app, giving teams a foundation for building internal tooling such as code analysis utilities, release-notes generators, and agents embedded in support workflows.
The Copilot CLI received a redesigned terminal user interface in /experimental mode, with tabbed access to pull requests, issues, and gists. A voice mode uses on-device speech-to-text, keeping audio on the local machine. An /every command schedules recurring prompts and background tasks.
Cloud automations let agents run on a schedule, respond to GitHub events, open issues, and post comments. The cloud agent asks permission before each write action by default, with an autopilot mode available once teams establish trust. The Copilot cloud agent can file issues, start discussions, and reply to reviewers.
Memory++ and the /chronicle command provide continuity across devices and over time, letting context from sessions started in the Copilot app, CLI, VS Code, or on GitHub be queried later.
“Partner-built agent apps integrate with GitHub Copilot to help automate tasks, generate code, analyze context, and execute actions. Use your favorite tools without leaving GitHub. Assign issues to new agents that fit your workflow. Partners include LaunchDarkly, Bright, Amplitude, Sonar, Endor Labs, Octopus Deploy, Packfiles, PagerDuty, and Miro. Start using these agent apps today,” Rodriguez concluded.