Pick your agent: Use Claude and Codex on Agent HQ

Source: GitHub Blog

Reducing Friction with Agent HQ

Context switching is the biggest source of friction in software development.
With the latest updates to Agent HQ, you can now run coding agents from multiple providers directly inside GitHub and your editor, keeping context, history, and review attached to your work.

What’s New

• Multiple coding agents are available for Copilot Pro+ and Enterprise users.
• Supported platforms:
  • GitHub (web)
  • GitHub Mobile
  • Visual Studio Code (Copilot CLI support coming soon)
• Agents you can run today (public preview):
  • GitHub Copilot
  • Claude by Anthropic
  • OpenAI Codex

Run agents directly from Agent HQ →

How It Works

• Stay in one place – No more hopping between tools.
• Preserve context – History, comments, and review data travel with you.
• Choose the right agent for each step – Move from idea to implementation using the most suitable model without losing momentum.

Claude in GitHub

• Claude can commit code and comment on pull requests directly from Agent HQ.
• Teams can iterate faster and ship with confidence, getting the reasoning power they need exactly where they need it.

“We’re bringing Claude into GitHub to meet developers where they are. With Agent HQ, Claude can commit code and comment on pull requests, enabling teams to iterate and ship faster and with more confidence.”
— Katelyn Lesse, Head of Platform, Anthropic

From Faster Code to Better Decisions

Agent HQ lets you compare how different agents approach the same problem. You can assign multiple agents to a task and see how Copilot, Claude, and Codex reason about trade‑offs and arrive at different solutions.

In practice, this helps you surface issues earlier by using agents for different kinds of review:

• Architectural guardrails – Ask one or more agents to evaluate modularity and coupling, helping identify changes that could introduce unintended side effects.
• Logical pressure testing – Use another agent to hunt for edge cases, async pitfalls, or scale assumptions that could cause problems in production.
• Pragmatic implementation – Have a separate agent propose the smallest, backward‑compatible change to keep the blast radius of a refactor low.

This method moves your reviews and thinking from syntax to strategy.

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’s vision of meeting developers wherever they work, and we’re excited to bring Codex to GitHub and VS Code. Codex helps engineers work faster and with greater confidence—and with this integration, millions more developers can now use it directly in their primary workspace, extending the power of Codex everywhere code gets written.

— Alexander Embiricos, OpenAI

Why Running Agents on GitHub Matters

GitHub is already where code lives, collaboration happens, and decisions are reviewed, governed, and shipped.

Making coding agents native to that workflow—rather than using external tools—makes them far more useful at scale. Instead of copying and pasting context between tools, documents, and threads, all discussion and proposed changes stay attached to the repository itself.

With Copilot, Claude, and Codex working directly in GitHub and VS Code, you can:

• Explore trade‑offs early – Run agents in parallel to surface competing approaches and edge cases before the code hardens.
• Keep context attached to the work – Agents operate inside your repository, issues, and pull requests instead of starting from stateless prompts.
• Avoid new review processes – Agent‑generated changes appear as draft pull requests and comments, reviewed the same way you’d review a teammate’s work.

There are no new dashboards to learn and no separate AI workflows to manage. Everything runs inside the environments you already use.

Built for Teams, Not Just Individuals

These workflows don’t only benefit individual developers. Agent HQ gives you org‑wide visibility and systematic control over how AI interacts with your codebase:

• Agent controls – Manage access and security policies in one place, allowing enterprise admins to define which agents and models are permitted across the organization.
• Code‑quality checks – GitHub Code Quality (public preview) extends Copilot’s security checks to evaluate the maintainability and reliability impact of changed code, helping ensure “LGTM” reflects long‑term health.
• Automated first‑pass review – A code‑review step is built directly into Copilot’s workflow, letting the agent catch initial problems before a developer sees the code.
• Impact metrics – Use the Copilot metrics dashboard (public preview) to track usage and impact across the organization, providing clear traceability for agent‑generated work.
• Security and auditability – Maintain full control with audit logging and enterprise‑grade access management, ensuring agents operate within your security posture.

This enables teams to adopt agent‑based workflows without sacrificing code quality, accountability, or trust.

More Agents Coming Soon

Access to Claude and Codex will soon expand to more Copilot subscription types. In the meantime, we’re actively working with partners—including Google, Cognition, and xAI—to bring more specialized agents into GitHub, VS Code, and Copilot CLI workflows.

Written by

Mario Rodriguez – Chief Product Officer, GitHub
Mario leads the GitHub Product team. A lifelong learner, his passion is building developer tools. Over the past 20 years he has held leadership roles at Microsoft and GitHub, most recently shaping GitHub’s AI strategy and the Copilot product line, launching Copilot across thousands of organizations and millions of users. Outside of work he enjoys time with his wife and two daughters and co‑chairs a charter school that supports education in rural U.S. communities.

Explore More from GitHub