IBL News | New York
GitHub continues embracing rival AI models and agents to improve its own Copilot offering. This month, it made available inside its platform the coding agents of Anthropic’s Claude and OpenAI’s Codex for users with a Copilot Pro Plus or Copilot Enterprise subscription.
Developers were are already able to access models from Anthropic, Google, xAI, Cognitiion, and OpenAI in GitHub Copilot, so the move is part of GitHub’s vision to make AI agents native. Now, developers can choose Copilot, Claude, Codex, or other custom agents when they’re creating a task.
Each coding agent consumes a premium request, and developers can assign agents to issues and pull requests. They can also weigh up how each agent performs and generates a solution.
GitHub’s approach is to avoid context swithing when developing software. “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,” said Mario Rodriguez, chief product officer at GitHub.
On the other hand, Microsoft is increasingly trialing Claude Code tool, even asking its own developers to Anthropic’s tool with GitHub Copilot, in an effort to improve GitHub Copilot.