{"id":231683,"date":"2025-10-29T08:16:16","date_gmt":"2025-10-29T08:16:16","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/231683\/"},"modified":"2025-10-29T08:16:16","modified_gmt":"2025-10-29T08:16:16","slug":"introducing-agent-hq-any-agent-any-way-you-work","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/231683\/","title":{"rendered":"Introducing Agent HQ: Any agent, any way you work"},"content":{"rendered":"<p>The current AI landscape presents a challenge we\u2019re all too familiar with: incredible power fragmented across different tools and interfaces. At GitHub, we\u2019ve always worked to solve these kinds of systemic challenges\u2014by making Git accessible, code review systematic with pull requests, and automating deployment with Actions.\u00a0<\/p>\n<p>With 180 million developers, <a href=\"https:\/\/github.blog\/news-insights\/octoverse\/octoverse-a-new-developer-joins-github-every-second-as-ai-leads-typescript-to-1\/\" rel=\"nofollow noopener\" target=\"_blank\">GitHub is growing at its fastest rate ever<\/a>\u2014a new developer joining every second. What\u2019s more, 80% of new developers are using Copilot in their first week. AI isn\u2019t just a tool anymore; it\u2019s an integral part of the development experience. Our responsibility is to ensure this new era of collaboration is powerful, secure, and seamlessly integrated into the workflow you already trust.<\/p>\n<p>At GitHub Universe, we\u2019re announcing Agent HQ, GitHub\u2019s vision for the next evolution of our platform. Agents shouldn\u2019t be bolted on. They should work the way you already work. That\u2019s why we\u2019re making agents native to the GitHub flow.<\/p>\n<p>Agent HQ transforms GitHub into an open ecosystem that unites every agent on a single platform. Over the coming months, coding agents from Anthropic, OpenAI, Google, Cognition, xAI, and more will become available directly within <a href=\"https:\/\/github.com\/features\/copilot\/plans?utm_source=blog-day1-recap-copilot-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">GitHub as part of your paid GitHub Copilot subscription<\/a>.<\/p>\n<\/p>\n<p>To bring this vision to life, we\u2019re shipping a suite of new capabilities built on the primitives you trust. This starts with a mission control, a single command center to assign, steer, and track the work of multiple agents from anywhere. It extends to VS Code with new ways to plan and customize agent behavior. And it is backed by enterprise-grade functionality: a new generation of agentic code review, a dedicated control plane to govern AI access and agent behavior, and a metrics dashboard to understand the impact of AI on your work.\u00a0<\/p>\n<p>We are also deeply committed to investing in our platform and strengthening the primitives you rely on every day. This new world of development is powered by that foundational work, and we look forward to sharing more updates.\u00a0<\/p>\n<p>Let\u2019s dive in.<\/p>\n<p>In this post<\/p>\n<p>GitHub is your Agent HQ: An open ecosystem for all agents\u00a0\u00a0<\/p>\n<p>The future is about giving you the power to orchestrate a fleet of specialized agents to perform complex tasks in parallel, not juggling a patchwork of disconnected tools or relying on a single agent. As the pioneer of asynchronous collaboration, we believe it\u2019s our responsibility to make sure these next-generation async tools just work.\u00a0<\/p>\n<p>With Agent HQ what\u2019s not changing is just as important as what is. You\u2019re still working with the primitives you know\u2014Git, pull requests, issues\u2014and using your preferred compute, whether that\u2019s GitHub Actions or self-hosted runners. You\u2019re accessing agents through your existing paid Copilot subscription.\u00a0<\/p>\n<p>On top of that foundation, we\u2019re opening the doors to a new world of capability. Over the coming months, coding agents from Anthropic, OpenAI, Google, Cognition, and xAI will be available on GitHub as part of your paid GitHub Copilot subscription.<\/p>\n<p>Don\u2019t want to wait? Starting this week, Copilot Pro+ users can begin working with \u00a0OpenAI Codex in <a href=\"https:\/\/code.visualstudio.com\/insiders\/\" rel=\"nofollow noopener\" target=\"_blank\">VS Code Insiders<\/a>, the first of our partner agents to extend beyond its native surfaces and directly into the editor.<\/p>\n<p><img data-recalc-dims=\"1\" decoding=\"async\" width=\"2796\" height=\"2022\" loading=\"lazy\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/Quotes_v5.jpg\" alt=\"'Our collaboration with GitHub has always pushed the frontier of how developers build software. The first Codex model helped power Copilot and inspired a new generation of AI-assisted coding. We share GitHub\u2019s vision of meeting developers wherever they work, and we\u2019re excited to bring Codex to millions more developers who use GitHub and VS Code, extending the power of Codex everywhere code gets written.' &#10;- Alexander Embiricos, Codex Product Lead, OpenAI&#10;&#10;'We\u2019re partnering with GitHub to bring Claude even closer to how teams build software. With Agent HQ, Claude can pick up issues, create branches, commit code, and respond to pull requests, working alongside your team like any other collaborator. This is how we think the future of development works: agents and developers building together, on the infrastructure you already trust.' &#10;- Mike Krieger, Chief Product Officer, Anthropic&#10;&#10;'The best developer tools fit seamlessly into your workflow, helping you stay focused and move faster. With Agent HQ, Jules becomes a native assignee, streamlining manual steps and reducing friction in everyday development. This deeper integration with GitHub brings agents closer to where developers already work, making collaboration more natural and efficient.'&#10;- Kathy Korevec, Director of Product at Google Labs\" class=\"wp-image-92035\"  \/><\/p>\n<p>Mission control: Your command center, wherever you build<\/p>\n<p>The power of Agent HQ comes from <a href=\"https:\/\/github.blog\/changelog\/2025-10-28-a-mission-control-to-assign-steer-and-track-copilot-coding-agent-tasks\/?utm_source=blog-day1-recap-mission-control-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">mission control<\/a>, a unified command center that follows you wherever you work. It\u2019s not a single destination; it\u2019s a consistent interface across GitHub, VS Code, mobile, and the CLI that lets you direct, monitor, and manage every AI-driven task. With mission control, you can choose from a fleet of agents, assign them work in parallel, and track their progress from any device.\u00a0<\/p>\n<p>We\u2019re also providing:\u00a0<\/p>\n<p>New branch controls that give you granular oversight over when to run CI and other checks for agent-created code.<\/p>\n<p>Identity features to control which agent is building the task, managing access, and policies just like you would with any other developer on your team.<\/p>\n<p>One-click merge conflict resolution, improved file navigation, and better code commenting capabilities.<\/p>\n<p>New integrations for Slack and Linear, on top of our recently announced connections for Atlassian Jira, Microsoft Teams and Azure Boards, and Raycast.\u00a0<\/p>\n<p><img data-recalc-dims=\"1\" decoding=\"async\" loading=\"lazy\" height=\"427\" width=\"1024\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/BlogImage_LogoWall_02.jpg\" alt=\"Logos for Slack, Linear, Microsoft Teams, VS Code, Azure Boards, Jira, and Raycast.\" class=\"wp-image-91940\"  \/><\/p>\n<p><a href=\"https:\/\/github.blog\/changelog\/2025-10-28-a-mission-control-to-assign-steer-and-track-copilot-coding-agent-tasks\/?utm_source=blog-day1-recap-mission-control-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">Try mission control today.<\/a><\/p>\n<p>New in VS Code: Plan, customize, and connect<\/p>\n<p>Mission control is in VS Code, too, so you\u2019ve got a single view of all your agents running in VS Code, in the Copilot CLI, or on GitHub.<\/p>\n<p>Today\u2019s brand new release in VS Code is all about working alongside agents on projects, and it\u2019s not surprising that great results start with a great plan. Getting the context right before a project is critical, but that same context needs to carry through into the work. Copilot already adapts to the way your team works by learning from your files and your project\u2019s culture, but sometimes you need more pointed context.<\/p>\n<p>So today, we\u2019re introducing Plan Mode, which works with Copilot, and asks you clarifying questions along the way, to help you to build a step-by-step approach for your task. Providing the context upfront improves what Copilot can do and helps you find gaps, missing decisions, or project deficiencies early in the process\u2014before any code is written. Once you approve, your plan goes to Copilot to start implementing, whether that\u2019s locally in VS Code or using an agent in the cloud.<\/p>\n<p>For even finer control, you can now create custom agents in VS Code with <a href=\"https:\/\/code.visualstudio.com\/docs\/copilot\/customization\/custom-instructions#_use-an-agentsmd-file-experimental?utm_source=blog-day1-recap-agents-md-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">AGENTS.md<\/a> files, source-controlled documents that let you set clear rules and guardrails such as \u201cprefer this logger\u201d or \u201cuse table-driven tests for all handlers.\u201d This shapes Copilot\u2019s behavior without you re-prompting it every time.<\/p>\n<p>Now you can rely on the new <a href=\"https:\/\/code.visualstudio.com\/docs\/copilot\/customization\/mcp-servers?utm_source=blog-day1-recap-mcp-registry-in-vs-code-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">GitHub MCP Registry<\/a>, available directly in VS Code. VS Code is the only editor that supports the full MCP specification. Discover, install, and enable MCP servers like Stripe, Figma, Sentry, and others, with a single click. When your task calls for a specialist, create custom agents in GitHub Copilot with their own system prompt and tools to help you define the ways you want Copilot to work.\u00a0<\/p>\n<p>Increased confidence and control for your team<\/p>\n<p>Agent HQ doesn\u2019t just give you more power\u2014it gives you confidence. Ensuring code quality, understanding AI\u2019s influence on your workflow, and maintaining control over how AI interacts with your codebase and organization are essential for your team\u2019s success, and we\u2019re tackling these challenges head-on.<\/p>\n<p>When it comes to code quality, the core problem is that \u201cLGTM\u201d doesn\u2019t always mean \u201cthe code is healthy.\u201d A review can pass, but can still degrade the codebase and quickly become long-term technical debt. With <a href=\"https:\/\/github.blog\/changelog\/2025-10-28-github-code-quality-in-public-preview\/?utm_source=blog-day1-recap-code-quality-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">GitHub Code Quality<\/a>, in public preview today, you\u2019ve got org-wide visibility, governance, and reporting to systematically improve code maintainability, reliability, and test coverage across every repository. Enabling it extends Copilot\u2019s security checks to look at the maintainability and reliability impact of the code that\u2019s been changed.<\/p>\n<p>And we\u2019ve added a code review step into the Copilot coding agent\u2019s workflow, too, so Copilot gets an initial first-line review and addresses problems (before you even see the code).\u00a0<\/p>\n<p><img data-recalc-dims=\"1\" decoding=\"async\" loading=\"lazy\" height=\"614\" width=\"1024\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/BlogImage_CodeQuality_01.jpg\" alt=\"Screenshot of GitHub Code Quality, showing the results of Copilot's review.\" class=\"wp-image-91946\"  \/><\/p>\n<p>As an organization, you need to know how Copilot is being used. So today, we\u2019re announcing the public preview of the <a href=\"https:\/\/github.blog\/changelog\/2025-10-28-copilot-usage-metrics-dashboard-and-api-in-public-preview\/?utm_source=blog-day1-recap-copilot-metrics-dashboard-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">Copilot metrics dashboard<\/a>, showing Copilot\u2019s impact and critical usage metrics across your entire organization.<\/p>\n<p>For enterprise administrators who are managing AI access, including AI agents and MCP, we\u2019re focused on providing consistent AI controls for teams with the <a href=\"https:\/\/github.blog\/changelog\/2025-10-28-enterprise-ai-controls-the-agent-control-plane-are-in-public-preview\/?utm_source=blog-day1-recap-control-plane-cta&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">control plane<\/a>\u2014your agent governance layer. Set security policies, audit logging, and manage access all in one place. Enterprise admins can also control which agents are allowed, define access to models, and obtain metrics about the Copilot usage in your organization.<\/p>\n<p>For developers, by developers\u00a0<\/p>\n<p>We built Agent HQ because we\u2019re developers, too. We know what it\u2019s like when it feels like your tools are fighting you instead of helping you. When \u201cAI-powered\u201d ends up meaning more context-switching, more babysitting, more subscriptions, and more time explaining what you need to get the value you were promised.\u00a0<\/p>\n<p>That ends today.<\/p>\n<p>Agent HQ isn\u2019t about the hype of AI. It\u2019s about the reality of shipping code.\u00a0 It\u2019s about bringing order and governance to this new era without compromising choice. It\u2019s about giving you the power to build faster, with more confidence, and on your terms.<\/p>\n<p>Welcome home. Let\u2019s build.\u00a0<\/p>\n<p><a href=\"https:\/\/github.blog\/changelog\/?label=universe25&amp;utm_source=blog-day1-recap-cta-to-changelog-roundup&amp;utm_medium=blog&amp;utm_campaign=universe25\" rel=\"nofollow noopener\" target=\"_blank\">See everything we shipped this year &gt;<\/a><\/p>\n<p>\t\tWritten by\t<\/p>\n<p>\t\t\t\t\t<img class=\"d-block circle\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/2501\" alt=\"Kyle Daigle\" width=\"80\" height=\"80\" loading=\"lazy\" decoding=\"async\"\/><\/p>\n<p>Kyle is Chief Operating Officer at GitHub, leading teams responsible for culture, developer outreach, operations, and communications. Joining GitHub in 2013, Kyle built and scaled GitHub\u2019s ecosystem engineering teams and worked on the acquisitions of Semmle, npm, and others. Eleven years (and many ships) later, Kyle is just as committed to driving growth across the business and its people, leading GitHub\u2019s own AI adoption strategy across a workforce of 3,000+ talented Hubbers. As a developer himself, Kyle is passionate about bringing software practices to operations and works to preserve and grow the spirit of GitHub as an AI-integrated, developer-first company. <\/p>\n<p>Prior to GitHub, Kyle took on developer-focused challenges as an engineering and product leader in startups, working in FinTech, real estate, and consulting. When he isn\u2019t collaborating with Hubbers and customers, he\u2019s building home automations with Home Assistant, working with nonprofits to make technology available and accessible to all, gaming (hello Xbox), and traveling with family.<\/p>\n","protected":false},"excerpt":{"rendered":"The current AI landscape presents a challenge we\u2019re all too familiar with: incredible power fragmented across different tools&hellip;\n","protected":false},"author":2,"featured_media":231684,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-231683","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/231683","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=231683"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/231683\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/231684"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=231683"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=231683"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=231683"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}