--- title: I used Claude Code, Codex, and Google Antigravity to... description: A hands-on comparison builds the same note-taking app using Claude Code (Claude Opus 5.5), Codex (GPT-6 Astra/Luna), and Google Antigravity, given the same... canonical: https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league | daily.dev og:description: A hands-on comparison builds the same note-taking app using Claude Code (Claude Opus 5.5), Codex (GPT-6 Astra/Luna), and Google Antigravity, given the same... og:url: https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse og:image: https://api.daily.dev/og/posts/8VcP9Qsse.png og:image:alt: I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league **[XDA Developers](https://daily.dev/sources/xda-developers)** · 7 min read · 0 upvotes · 0 comments ## Summary A hands-on comparison builds the same note-taking app using Claude Code (Claude Opus 5.5), Codex (GPT-6 Astra/Luna), and Google Antigravity, given the same open-ended prompt. Codex produced the most polished, cohesive, and feature-complete result (Folio), thoroughly testing workflows before finishing. Claude Code (Margin) was technically impressive but over-engineered unrequested features and had a less cohesive UI. Antigravity rushed to declare the project done despite missing several explicitly requested features, though it fixed issues once flagged. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Which AI coding tool produced the best result when building the same note-taking app, Claude Code, Codex, or Google Antigravity? Codex produced the best result, building a polished, cohesive note-taking app called Folio using GPT-6 Astra (later GPT-6 Luna) at high/medium reasoning. It stayed focused on the requested features, thoroughly tested workflows like note persistence, search, and canvas exports, and delivered the most aesthetically appealing and usable UI compared to Claude Code's Margin and Google Antigravity's output. _See how daily.dev surfaces real-world comparisons like this before you commit to an AI coding tool._ ### What went wrong when Google Antigravity built a note-taking app from a feature-complete prompt? Antigravity declared the project finished before completing several explicitly requested features, including PDF annotation, audio recording, and backlink parsing, listing them as future work even though they were part of the original brief. It also needed help migrating a Tailwind setup and fixing TypeScript issues before the app ran correctly. _Developers weighing agentic coding tools can track experience reports like this on daily.dev._ ### How much output did Claude Opus 5.5 generate compared to Codex when building the same app in an agentic coding session? Claude Opus 5.5 generated around 489,000 output tokens and reported 75.3 million prompt-cache reads, versus roughly 82,000 output tokens for Codex on the same task. Despite the far larger output volume, Claude's resulting app, Margin, felt less polished and cohesive than Codex's Folio, partly due to Claude building unrequested features. _Anyone comparing token usage and output quality across coding agents can follow analyses like this on daily.dev._ ## Similar posts on daily.dev - [I asked Claude Code, Codex, and Google Antigravity to rebuild the same website; one is in a different league](https://daily.dev/posts/i-asked-claude-code-codex-and-google-antigravity-to-rebuild-the-same-website-one-is-in-a-differen-nkjtim7nk) · XDA Developers · 0 upvotes · 0 comments - [I created a complex web app using Claude Code, Codex, and Antigravity, and only one acted like a tech lead](https://daily.dev/posts/i-created-a-complex-web-app-using-claude-code-codex-and-antigravity-and-only-one-acted-like-a-tec-kocwdvbfi) · XDA Developers · 0 upvotes · 0 comments - [I created a complex website using Claude Code, Codex, and Google Antigravity, and only one of them behaved like a senior developer](https://daily.dev/posts/i-created-a-complex-website-using-claude-code-codex-and-google-antigravity-and-only-one-of-them-b-sqqrpk4ll) · XDA Developers · 0 upvotes · 0 comments - [Claude Code vs. Cursor vs. Codex vs. Antigravity — six months in](https://daily.dev/posts/claude-code-vs-cursor-vs-codex-vs-antigravity-six-months-in-stlje26sf) · The New Stack · 0 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#claude-code](https://daily.dev/tags/claude-code), [#vibe-coding](https://daily.dev/tags/vibe-coding), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league","url":"https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse"},"datePublished":"2026-10-04T21:34:02.949Z","dateModified":"2026-10-04T22:03:07.471Z","description":"A hands-on comparison builds the same note-taking app using Claude Code (Claude Opus 5.5), Codex (GPT-6 Astra/Luna), and Google Antigravity, given the same...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2be1ab14a6b6168938ac62d8e52a7129?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2be1ab14a6b6168938ac62d8e52a7129?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,claude-code,vibe-coding,openai-codex","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/i-used-claude-code-codex-and-google-antigravity-to-build-my-dream-note-taking-app-and-one-is-in-a-8vcp9qsse#faq","mainEntity":[{"@type":"Question","name":"Which AI coding tool produced the best result when building the same note-taking app, Claude Code, Codex, or Google Antigravity?","acceptedAnswer":{"@type":"Answer","text":"Codex produced the best result, building a polished, cohesive note-taking app called Folio using GPT-6 Astra (later GPT-6 Luna) at high/medium reasoning. It stayed focused on the requested features, thoroughly tested workflows like note persistence, search, and canvas exports, and delivered the most aesthetically appealing and usable UI compared to Claude Code's Margin and Google Antigravity's output. See how daily.dev surfaces real-world comparisons like this before you commit to an AI coding tool."}},{"@type":"Question","name":"What went wrong when Google Antigravity built a note-taking app from a feature-complete prompt?","acceptedAnswer":{"@type":"Answer","text":"Antigravity declared the project finished before completing several explicitly requested features, including PDF annotation, audio recording, and backlink parsing, listing them as future work even though they were part of the original brief. It also needed help migrating a Tailwind setup and fixing TypeScript issues before the app ran correctly. Developers weighing agentic coding tools can track experience reports like this on daily.dev."}},{"@type":"Question","name":"How much output did Claude Opus 5.5 generate compared to Codex when building the same app in an agentic coding session?","acceptedAnswer":{"@type":"Answer","text":"Claude Opus 5.5 generated around 489,000 output tokens and reported 75.3 million prompt-cache reads, versus roughly 82,000 output tokens for Codex on the same task. Despite the far larger output volume, Claude's resulting app, Margin, felt less polished and cohesive than Codex's Folio, partly due to Claude building unrequested features. Anyone comparing token usage and output quality across coding agents can follow analyses like this on daily.dev."}}]} ```