GitHub has launched a GitHub Copilot desktop software for agent-based software program growth. The app is in technical preview for current Copilot Professional, Professional+, Enterprise and Enterprise customers.
The desktop app is designed as a central workspace for builders managing a number of AI agent periods directly. It brings energetic periods, points, pull requests and background automations right into a single “My Work” view throughout related repositories.
Every session runs in its personal git worktree, giving builders an remoted copy of a department whereas an agent investigates a bug, works on a backlog merchandise or responds to evaluation suggestions. The app manages these worktrees routinely, eradicating the necessity for guide department setup and cleanup.
GitHub has additionally added Agent Merge, a instrument that follows a pull request by way of checks, evaluations and merging. Builders can select whether or not Copilot ought to handle failing steady integration checks, reply to evaluation feedback, or full the merge as soon as set situations are met.
Management centre
GitHub introduced the launch as a response to the rising use of AI brokers in software program engineering and the administration challenges that include them. Builders are more and more transferring between prompts, planning, coding, evaluation and merging by way of AI-assisted workflows, however current instruments typically depart work unfold throughout a number of home windows and interfaces.
The corporate additionally pointed to rising exercise on its platform. Commits on GitHub have practically doubled 12 months on 12 months to greater than 1.4 billion a month, whereas GitHub Actions is dealing with greater than 2 billion minutes every week.
That progress is placing extra stress on evaluation and validation. One goal of the brand new desktop expertise is to make agent work simpler to examine, so builders can see what was tried, what was validated and the place human intervention remains to be wanted.
A brand new function referred to as canvases sits alongside the app. GitHub described them as shared work surfaces that may show a plan, pull request, browser session, terminal, deployment, dashboard or workflow state, permitting each the developer and the agent to replace the identical view.
The goal is to maneuver agent output past chat threads right into a format the place actions and selections are seen in a single place. Builders can edit, reorder, approve or redirect work instantly throughout the canvas.
Sandbox controls
GitHub can also be increasing how Copilot brokers run code by providing each native and cloud sandboxes. The aim is to let brokers take a look at and iterate in contained environments with out affecting manufacturing programs.
Within the native model, Copilot runs in an remoted atmosphere on the consumer’s machine with restricted entry to recordsdata, networks and system features. Native sandbox insurance policies will be centrally configured and enforced.
Within the cloud possibility, every sandbox runs in an remoted momentary Linux atmosphere hosted by GitHub. Organisations can set their very own insurance policies, and customers can resume periods remotely from completely different gadgets.
Evaluate modifications
GitHub has additionally up to date Copilot code evaluation instruments to deal with the bigger variety of pull requests AI brokers could generate. Customers can now lengthen code evaluation by way of customized agent abilities, MCP server connections and configurable GitHub Actions workflows.
A medium-tier evaluation possibility has been launched, sending pull requests to what GitHub referred to as a higher-reasoning mannequin. Repository directors can assign both low or medium steering ranges relying on a repository’s threat or significance.
GitHub has additionally added a “/security-review” talent for security-focused checks. A “/rubberduck” talent is now typically accessible and may use a number of mannequin households to critique an implementation and establish points.
Help for Copilot code evaluation has additionally been prolonged to Azure DevOps, giving customers one-click evaluation, inline feedback and repair strategies in that atmosphere.
Broader ecosystem
Outdoors the desktop app, GitHub stated its Copilot SDK is now typically accessible in Node.js/TypeScript, Python, Go, .NET, Rust and Java. The software program growth package offers builders entry to the identical runtime utilized by the Copilot app to construct inside instruments and customized brokers.
Copilot CLI has additionally been up to date with a redesigned terminal interface, voice enter utilizing on-device speech-to-text, and scheduled duties. Cloud automations can now let brokers run on a schedule, react to GitHub occasions, open points and depart feedback, with permission requested earlier than every write motion by default.
GitHub can also be increasing integration with exterior software program distributors by way of partner-built agent apps embedded in GitHub. Named companions embody LaunchDarkly, Brilliant, Amplitude, Sonar, Endor Labs, Octopus Deploy, Packfiles, PagerDuty and Miro.
One buyer, Avanade, stated the product offers engineering groups a single place to direct a number of agent-led duties.
“The GitHub Copilot app is the newest in a line of AI tooling from GitHub that’s remodeling our enterprise. Shifting past AI help, the app has supplied a much-needed management middle for agentic growth. Our ahead deployed engineers can dispatch a cohort of brokers and handle a number of initiatives, all from one location. Easy accessibility to plans and autopilots with the power to run interactive periods or step into code the place wanted,” stated David Jobling, Grasp Expertise Architect, Head of Expertise & Supply Futures, International Solutioning & Supply, Avanade.