Any AI. One file. 90 minutes. We rank the human.
VIBELADDER is a weekly, time-boxed "vibe-coding" competition where participants have 90 minutes to build a small complete app using any AI tools; entries are single-file HTML submissions judged head-to-head, earning an Elo-style rating and published replays with full prompt transcripts.
Any AI. One file. 90 minutes. We rank the human. is coding software teams evaluate for software & gaming. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: Software & Gaming
What it does
Coding software for decision-makers comparing workflow fit and alternatives.
Best fit
Software & Gaming
Pricing snapshot
Free from Free
Next step
Compare Any AI. One file. 90 minutes. We rank the human. with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
VIBELADDER is a weekly vibe-coding competition (Season 1) where a small, secret task drops each Saturday and participants have 90 minutes to build a small, complete app using any AI tools. Submissions must be a single self-contained HTML file that works offline, and entrants must provide their full session transcript or a screen recording. Submissions that pass a functional smoke test enter head-to-head pairwise judging against a rubric; results update an Elo-style rating and winning runs are published with annotated replays and transcripts.
Task drops Saturday. 90 minutes. Bring whatever AI you want — we rank the human.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
90-minute timed rounds
Each task drops simultaneously for all competitors on Saturday; you have 90 minutes from the drop to submit, enforced by submission timestamp.
Any AI tool allowed
Competitors may use any AI tool or model (examples listed: Claude Code, Cursor, Copilot, Windsurf, raw API); the tool choice is declared but the human is ranked.
Single-file HTML deliverable
Submissions must be one self-contained HTML file that works opened from disk with the network off — no external scripts, fonts, or API calls.
Transcript / anti-cheat requirement
A full session export or screen recording must accompany each entry; no transcript means no entry. Top finishers' transcripts are audited before results publish.
Head-to-head judging & Elo-style rating
Submissions passing a mechanical smoke test are compared pairwise against the round rubric; results feed an Elo/Bradley-Terry-style rating that carries across rounds.
Published replays
Every winning run is published with its full prompt transcript and annotated replays are published for winners.
Verified seats and public nicknames
Seats are held with Google or GitHub sign-in (private); only the chosen public nickname is shown to enforce one seat per person.
Pricing
Season 1 is free; there are deliberately no monetary prizes in Season 1.
Season 1
Free- Participation in weekly rounds
- Elo-style rating
- Published replay and transcript for winning runs
- Season badge
Use Cases
Skill-building in AI-assisted coding
Practice prompting and directing AI to build small, functional apps under a strict time limit; the ladder measures how effectively a human directs AI.
Public showcase and learning
Winners' prompt transcripts and annotated replays are published, providing concrete examples and learning material for others.
Competitive ranking and community
Participants build a persistent Elo-style rating across rounds to compare performance over a season and across players.
Accessible entry for non-expert coders
The format allows people with little syntax knowledge to enter by directing AI rather than hand-coding, as explicitly stated.
Integrations
AI tools (any)
Participants may use any AI tool or model (examples cited: Claude Code, Cursor, Copilot, Windsurf, raw API).
Google / GitHub sign-in
Sign-in via Google or GitHub is required to hold a season seat (login is private; only your chosen nickname is shown).
Benefits
Limitations
Frequently Asked Questions
What kind of tasks?
Why record my prompts?
How exactly is judging done?
Can I enter with no coding experience?
Why is there no prize money?
What if I can't make a Saturday?
Why do I sign in with Google or GitHub?
Who runs this?
Getting Started
- 1 Claim a seat by signing in with Google or GitHub to reserve your nickname for the season.
- 2 Show up on Saturday at the scheduled drop time (task drops Saturday 17:00 CET) and open the unlocked submission page.
- 3 Build within the 90-minute window and submit a single self-contained HTML file plus your full session transcript or screen recording before the deadline.
Support
docs
Site pages including the submission page, rules, schedule, leaderboard, and sponsors page provide event details and published results.
API
Compare Any AI. One file. 90 minutes. We rank the human. with similar tools
See how it stacks up against alternatives
Related Tools
View all 64 →
Agent.reviews
Agent.reviews is a software discovery and review site where coding agents can compare tools and publish reviews based on real tasks. People can browse tools and categories, read reviews, and add the review workflow to an agent.
FixBugs
FixBugs is an AI debugging agent for SREs and on-call engineers that auto-triages alerts, performs AI-powered root cause analysis, reproduces issues, and generates validated code fixes with reproduction tests. Available as a VS Code extension and GitHub App with native integrations for GitLab, Jira and more.
please do not escape
A curated dataset of sandbox environments for AI coding agents, published with a raw YAML data file and hosted on GitHub; intended as a discoverable, contributor-driven collection of examples and primary-source references.
Sentrint
Sentrint is a code-security scanner that analyzes repositories for hardcoded secrets, access rules, vulnerable dependencies and dangerous code paths, uses an AI layer to filter false positives and generates platform-specific fix prompts, and returns a numeric grade, findings in plain English, and a live badge.
GIDE, Your AI Coding Command Center
GIDE is a local-first, agentic AI coding IDE and CLI that runs LLMs on your machine to edit code, run commands, and verify changes—offline, with zero per-token cost, an OpenAI-compatible local API, and gated file writes for safe automation.
Premium Alternatives
templateai
TemplateAI is a paid Next.js 13 full‑stack starter template that bundles authentication, payments, database, and AI features (text, image generation, vector search) so developers can build and launch AI apps faster.
shipflutter
ShipFlutter is a customizable Flutter starter kit and AI-powered builder that combines Flutter, Firebase, and Vertex AI to generate production-ready, responsive Android, iOS, and Web apps quickly. It is offered as purchasable starter or lifetime licenses with templates, backend integrations, and deployment-ready features.
techscreen
TechScreen is a desktop AI interview assistant for macOS and Windows that listens to interview questions or reads typed prompts and displays suggested answers live. It supports coding, system design, and behavioral interviews, with a window designed to stay out of screen shares and recordings.
Augment Code's Cosmos
Augment Code's Cosmos is an enterprise unified agents platform that runs software development agents at organizational scale, providing a Context Engine, agent runtime, reusable Experts, and security controls to accelerate code review, testing, incident response, and other SDLC workflows.