Essay/Claude Code·May 16, 2026

GitHub Copilot Now Lets You Run Claude and Codex Agents Natively—No Switching Required

GitHub shipped a quiet but significant move: Claude and Codex are now available as native agents inside Copilot for Business and Pro...

Luke Thompson
Luke ThompsonMay 16, 2026 · 3 min read
In this article
GitHub Copilot Now Lets You Run Claude and Codex Agents Natively—No Switching Required
GitHub shipped a quiet but significant move: Claude and Codex are now available as native agents inside Copilot for Business and Pro subscribers. You don't need another tab, another extension, or another API key. Just enable it and swap between models inside your editor. This is how multi-model development should work—and it changes the calculus for teams choosing coding assistants.
Introducing Claude Code — Official Anthropic

What Changed

GitHub announced in February (just made broader recently) that Claude and Codex are now third-party agents inside Copilot. Access rolls out to Copilot Business and Copilot Pro users—Enterprise and Pro+ already had this capability. Each agent session consumes one premium request from your Copilot quota, so no separate billing. The agents run natively inside github.com, GitHub Mobile, and VS Code. OpenAI Named Gartner Leader for Enterprise AI C...

Here's what matters: The agents aren't just text-in, text-out. They can access your repository code, commit history, pull requests, issues, and Copilot Memory. They share context across surfaces, meaning you can start a session in VS Code, context travels to github.com, and everything's consistent. GitHub calls this the "Agent Control Plane," and it's now generally available.

Why This Matters

The old workflow: You'd pick one AI coding tool and live with it. Try Claude? Switch extensions. Try Codex? Switch again. Context was scattered. Governance was a nightmare. Now? Both are inside your existing tool, under one billing model, with centralized audit logs and policy management.

For enterprises, this is huge. Security teams get a single control point (Agent Control Plane) for enabling/disabling agents, setting organization-wide policies, and reviewing audit logs. No shadow AI tools. No "well, she's using Claude outside the company console." Everything is visible and governed from one place.

Field note

Multi-model support inside a single IDE wasn't supposed to work this smoothly. GitHub nailed the integration—billing, context, governance, and UX are all seamless.

The Developer UX Angle

For practitioners, this is about reduced friction. You're already in GitHub and VS Code. You don't adopt a new tool; you just enable a new agent. Context—your repo, your PRs, your history—flows automatically. You can compare Claude output against Codex output without leaving the editor. This is what the multi-model AI future actually looks like.

GitHub also noted that agents can open draft PRs, handle asynchronous sessions (start a task, come back later), and log detailed activity for review. Translation: These aren't simple autocomplete models. They're full agents that can drive workflows.

What This Means For You

If you're on GitHub and VS Code: This is essentially free—you likely already have Copilot. Toggle it on and evaluate Claude for your workflows. If you're a team lead or CTO: This solves a governance problem you probably didn't know you could solve. Centralized policies, audit logs, and model choice without losing control.

Watch the quota model closely. Each session consumes one "premium request"—unclear if drafting a PR costs more than a code suggestion. GitHub's usually generous with quotas, but if you're running high-volume agent workloads, clarify before rolling out to teams. Beyond that: This is a net win for developers. Model choice, in your existing workflow, with full context. That's hard to argue with.

Sources & Further Reading

Related essay
Claude Code Review Tool: How It Works and What It Costs
Related essay
Claude Code's Billing Just Split on June 15 — Here's What CEOs and Finance Leaders Need to Know About the New Agent Credit Model
Related essay
How to Use Claude Code Routines: The Complete Setup Guide

THE CLAUDE INSIDER

Get the Claude playbook in your inbox.

One weekly email for Claude and Claude Code users. Real workflows, no hype. Subscribe and we send you The Claude Power-User Cheatsheet.

GUIDES AND COMPARISONS

— ¶ —

Luke Thompson

Luke Thompson

Editor-in-Chief · The Claude Insider

Luke Thompson is the founder of The Operations Guide, LLC and editor of The Claude Insider. Based in Jonesborough, Tennessee, he has spent years building AI-augmented business systems and automation workflows for operators and teams. He began working with large language models in production well before the current wave of consumer AI tools, integrating them into client workflows, content pipelines, and operational infrastructure. At The Claude Insider, he writes about Claude with the specificity of someone who uses it daily as a professional tool — not as a reviewer or commentator, but as a builder. His coverage focuses on what actually works: prompt patterns, API integration strategies, agentic workflows, and the real-world tradeoffs that practitioners face. He is not affiliated with Anthropic, PBC.

Articles are researched and drafted with AI assistance, reviewed and edited by Luke Thompson.

From Reading to Action

Know where AI can pay off in your company.

Take the free two-minute AI Readiness Assessment. See your score, the two gaps holding you back, and the next move worth making.

Get your readiness score

Instant report · No account to start

Related reading

View archive →