During its annual conference, GitHub Universe, GitHub shared its plans for Agent HQ, its vision for the future of the platform where AI agents are natively integrated across all of GitHub.
As part of this Agent HQ initiative, over the next several months, paid GitHub Copilot users will gain direct access to popular coding agents from Anthropic, OpenAI, Google, Cognition, xAI, and more.
Agent HQ brings with it several new capabilities to support this next evolution, the first of which is mission control, a central command center for assigning, steering, and tracking the work of multiple agents across GitHub, Copilot CLI, and VS Code.
Mission control’s branch controls gives developers granular oversight over running checks for code created by the agents. Identity features will also be introduced to allow developers to manage agents like they would other coworkers and control which agent is building a task, manage access, and implement policies.
Other mission control features include one-click conflict resolution, improved file navigation, better code commenting capabilities, integrations for Slack and Linear, and a metrics dashboard so that developers can understand the impact of AI on their work.
In VS Code, Plan Mode is being introduced. In this new mode, Copilot will ask clarifying questions as it helps build a step-by-step plan. “Providing the context upfront improves what Copilot can do and helps you find gaps, missing decisions, or project deficiencies early in the process—before any code is written. Once you approve, your plan goes to Copilot to start implementing, whether that’s locally in VS Code or using an agent in the cloud,” Kyle Daigle, COO of GitHub wrote in a blog post.
VS Code users will also be able to create custom agents with AGENTS.md files, which let developers set clear rules and guardrails, such as “use table-driven tests for all handlers.” VS Code also now has access to GitHub’s MCP Registry.
Additionally, GitHub is also introducing a public preview for GitHub Code Quality, which provides in-context feedback about the quality of code, reliability and maintainability scores, and one-click Copilot fixes. A code review step was also added into the Copilot coding agent workflow to perform an initial review before it even shares the generated code with the developer.
And finally, the company announced a public preview for the Copilot metrics dashboard, which shows developers Copilot’s impact and critical usage metrics.
“We built Agent HQ because we’re developers, too. We know what it’s like when it feels like your tools are fighting you instead of helping you. When “AI-powered” ends up meaning more context-switching, more babysitting, more subscriptions, and more time explaining what you need to get the value you were promised. That ends today. Agent HQ isn’t about the hype of AI. It’s about the reality of shipping code. It’s about bringing order and governance to this new era without compromising choice. It’s about giving you the power to build faster, with more confidence, and on your terms,” Daigle wrote.
