OpenAI Codex CLI vs GitHub CopilotUpdated 2026-03-16

SUMMARY

OpenAI Codex CLI (CLI) uses markdown configuration while GitHub Copilot (IDE) uses markdown. They differ on 3 of 11 compared features. Both tools provide AI-assisted development but take different approaches to project configuration.

FEATURE COMPARISON

FeatureOpenAI Codex CLIGitHub Copilot
Config formatmarkdownmarkdown
Hierarchy support
Global config
Project config
Subdirectory scoping
File inclusion / imports
Ignore file.codexignore
IDE integrationCLI
Schema / structureFree-form (Markdown)Free-form (Markdown)
Git committed
EncodingUTF-8UTF-8

FILE MAPPING

PurposeOpenAI Codex CLIGitHub Copilot
Project instructionsAGENTS.md.github/copilot-instructions.md
Project instructionsAGENTS.override.md.github/instructions/*.instructions.md

SIDE-BY-SIDE CODE SAMPLES

OpenAI Codex CLI
AGENTS.md
markdown
# AGENTS.md

## Project Overview

This is a Next.js 14 e-commerce application using the App Router,
Server Components, and Drizzle ORM with PostgreSQL.

## Code Conventions

- Use TypeScript strict mode throughout
- Prefer Server Components; use "use client" only when necessary
- Name files with kebab-case: `product-card.tsx`, not `ProductCard.tsx`
- Co-locate tests: `product-card.test.tsx` next to `product-card.tsx`

## Architecture

- `app/`           — Next.js App Router pages and layouts
- `components/`    — Shared UI components
- `lib/`           — Utilities, database client, auth helpers
- `actions/`       — Server Actions for mutations

## Testing

- Use Vitest for unit tests, Playwright for E2E
- Mock database calls using `lib/test-utils.ts` helpers
- Every new component needs at least one test

## Build Commands

```bash
pnpm dev          # Start dev server
pnpm build        # Production build
pnpm test         # Run Vitest
pnpm test:e2e     # Run Playwright
pnpm lint         # ESLint check
```
GitHub Copilot
.github/copilot-instructions.md
markdown
# Copilot Instructions

## Code Style
- Use TypeScript strict mode for all new files
- Prefer functional components with hooks over class components
- Use named exports, not default exports

## Libraries
- Use date-fns for date manipulation (not moment.js)
- Use zod for runtime validation
- Prefer fetch over axios for HTTP requests

## Testing
- Write tests using Vitest
- Use Testing Library for component tests
- Aim for integration tests over unit tests

## Conventions
- Use camelCase for variables, PascalCase for components
- Prefix interfaces with I (e.g., IUserProps)
- Keep files under 300 lines; extract if longer

KEY DIFFERENCES

1. Global config

OpenAI Codex CLI: Supported. GitHub Copilot: Not supported.

2. Ignore file

OpenAI Codex CLI: .codexignore. GitHub Copilot: Not supported.

3. IDE integration

OpenAI Codex CLI: CLI. GitHub Copilot: Supported.

WHICH SHOULD I USE?

Recommendation

Choose based on your IDE/CLI preference. If you use OpenAI Codex CLI, configure AGENTS.md. If you use GitHub Copilot, configure .github/copilot-instructions.md. Many projects include config files for multiple tools so each team member can use their preferred editor.

PORTABILITY TIP

sync-instructions.sh
bash
# Maintain a single source of truth:
cp AI-INSTRUCTIONS.md CLAUDE.md
cp AI-INSTRUCTIONS.md .cursorrules
cp AI-INSTRUCTIONS.md AGENTS.md

SEE ALSO

agentconfig.ing2026-03-16COMPARE(1)