GitHub is giving developers access to third-party AI coding agents with the launch of a new “Agent HQ.” Instead of just using GitHub Copilot, developers will get to try OpenAI’s Codex, Anthropic’s Claude, Google’s Jules, xAI, and Cognition’s Devin within GitHub in the coming months.
Developers with a GitHub Copilot subscription will be able to access a new “mission control” dashboard, where they can control, manage, and track multiple AI coding agents. “With the new set of AI controls, we’re providing a control plane for all of the agent use on GitHub, whether you’re using the GitHub coding agent or one of our partners’ coding agents inside the platform,” GitHub COO Kyle Daigle tells The Verge.
GitHub’s new Agent HQ will also allow developers to run multiple AI agents in parallel as they complete the same task. That way, developers can choose which agent’s work they like the best. Ahead of Agent HQ’s official launch, GitHub is making OpenAI Codex available to Copilot Pro Plus users who are part of the VS Code Insiders program.
Additionally, GitHub is launching a few other tools, including a new Plan Mode in VS Code that uses Copilot to create a step-by-step plan for a task that its AI coding agent will later execute. GitHub is also adding a code review step to Copilot, allowing the agent to access tools, such as CodeQL, that it can use to evaluate code before passing it along to a developer.