GitHub adds Claude and Codex AI coding agents to improve workflow efficiency

GitHub adds Claude and Codex AI coding agents

GitHub is making Claude by Anthropic and OpenAI's Codex AI coding agents directly available inside GitHub today. A new public preview adds Claude and Codex to GitHub, GitHub Mobile, and Visual Studio Code, for users with a Copilot Pro Plus or Copilot Enterprise subscription. The move is part of Agent HQ, GitHub's vision to make AI agents native to how developers use GitHub every day. Developers can now choose Copilot, Claude, Codex or other custom agents when they're creating a task. Each coding agent will consume a premium request, and developers can assign agents to issues and pull requests. Developers will also be able to judge how Copilot, Claude, and Codex perform, and weigh up how each AI coding agent has generated a solution. "Context switching equals friction in software development," says Mario Rodriguez, chief product office at GitHub. "With Codex, Claude, and Copilot in Agent HQ, you can move from idea to implementation using different agents for different steps without switching tools or losing context." GitHub has been quick to embrace rival AI models and agents to improve its own Copilot offering. Developers are already able to access models from Anthropic, Google, xAI, and OpenAI in GitHub Copilot, so integrating in rival AI coding agents feels like a natural next step. Access to Claude and Codex will expand to more GitHub Copilot subscription types soon, and GitHub is also working with Google, Cognition, and xAI to bring more agents into GitHub, Visual Studio Code, and the Copilot CLI. GitHub's embrace of rival AI coding agents comes as Microsoft is increasingly trialing Anthropic's Claude Code tool. Developers inside Microsoft have been asked to compare Claude Code with GitHub Copilot, in an effort to improve GitHub Copilot.

GitHub integrates Claude and Codex AI coding agents directly into GitHub

Workers can collaborate by leaving @comments with agents just like human colleagues Microsoft-owned GitHub has added support for more AI coding agents within its ecosystem, including Anthropic's Claude and OpenAI's Codex, in the hope of attracting and retaining users who want more flexibility. Users will now be able to choose between Copilot, Claude or Codex agents or select their own custom agents, which will work across the website, the mobile app and VS Code. "You can do this directly from issues, pull requests, the Agents tab in enabled repositories, and the agent sessions view in VS Code for a seamless cross-client experience," the company wrote in an announcement. Claude and Codex will be available to Copilot Pro+ and Copilot Enterprise subscribers as part of their plan, but access isn't unlimited - instead, each agent session consumes one premium request during public preview. Formal pricing is expected to be established later on. GitHub shared instructions on how to assign agents using the Copilot icon in the input field, but the company also mentioned that multiple agents can be used to produce a draft pull request. Users can also leave review comments or request changes by using @copilot, @claude or @codex, making bringing working with AI agents in line with working with human colleagues. "Our goal is to give developers the reasoning power they need, right where they need it," Anthropic Head of Platform Katelyn Lesse wrote. "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," OpenAI Product member Alexander Embiricos added. GitHub Chief Product Officer Mario Rodriguez confirmed that more agents are in the pipeline, including collaborations with Google, Cognition and xAI.