Google Antigravity vs OpenAI Codex CLIUpdated 2026-03-18

SUMMARY

Google Antigravity (IDE) uses markdown configuration while OpenAI Codex CLI (CLI) 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

FeatureGoogle AntigravityOpenAI Codex CLI
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

PurposeGoogle AntigravityOpenAI Codex CLI
Project instructionsAGENTS.mdAGENTS.md
Project instructionsGEMINI.mdAGENTS.override.md
skillsresources/*/SKILL.md.agents/skills/*/SKILL.md

SIDE-BY-SIDE CODE SAMPLES

Google Antigravity
AGENTS.md
markdown
# Project Instructions

## Architecture
- Monorepo with apps/ and packages/ directories
- Each app is a standalone Next.js deployment
- Shared packages use TypeScript project references

## Code Standards
- TypeScript strict mode everywhere
- Use Zod for runtime validation at API boundaries
- Prefer server components; use "use client" only when needed
- All database queries go through the data-access layer

## Testing
- Unit tests with Vitest for business logic
- Integration tests for API routes
- E2E tests with Playwright for critical user flows

## Deployment
- Preview deployments on every PR
- Production deploys from main branch only
- Environment variables managed via .env.local (never committed)
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
```

KEY DIFFERENCES

1. Global config

Google Antigravity: Not supported. OpenAI Codex CLI: Supported.

2. Ignore file

Google Antigravity: Not supported. OpenAI Codex CLI: .codexignore.

3. IDE integration

Google Antigravity: Supported. OpenAI Codex CLI: CLI.

WHICH SHOULD I USE?

Recommendation

Choose based on your IDE/CLI preference. If you use Google Antigravity, configure AGENTS.md. If you use OpenAI Codex CLI, configure AGENTS.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.ing2026-03-18COMPARE(1)