Crowded

Built with gpt-5.6

719 projects in the corpus already ship on it. Expect company.

Reviewed ideas using gpt-5.6 (25 of 30)

• BOB Forge — openLocal Codex diagnoses the incident. BOB Forge isolates and tests the patch, binds phone approval to the exact bytes, deploys, verifies, and rolls back locally.
• SlopGuard — openCodex-powered PR review that catches what only AI-generated code gets wrong: hallucinated packages, silent scope creep, and dropped auth checks.
• ClassLens — openDiagnoses what an Algebra-1 class misunderstands from their wrong answers, then builds a recheck quiz that verifies the fix. 41.1% @1 measured on 716 held-out real student answers.
• ArtSoul Protocol — openCollector demand comes before minting: discover, bid, settle, then mint digital art on Base.
• The Committee — Explainable AI Paper-Trading Lab — openAn auditable AI committee that debates real market data, exposes risk and dissent, only opens simulated paper-trading positions and you can see the debate between the agents for more transparency.
• GPTDesign: The Design Layer for Codex — openGive any coding agent taste: GPTDesign locks design systems as law, streams agent-built pages live, and machine-verifies every button before handoff, powered by Codex and GPT-5.6.
• workspace.json for Codex — openPortable codebase intelligence for Codex, combining workspace.json evidence, focused MCP context, and deterministic pre-edit risk checks.
• Amadeus Skill — openAmadeus is a local-first control plane for coding agents. It compiles human-approved runs into compact skills via Codex CLI (no API key needed) for secure, opt-in procedural memory.
• Deep Dive Skill — openAn adversarially-verified deep-research CLI skill that runs on 15 different AI coding agents — including Codex — and refuses to trust any claim until independent verifier agents fail to refute it.
• PetShare — openPet-first shared-travel planning that checks hard constraints before GPT-5.6 explains the eligible supplied plan.
• Foresight — openPredicts the right GPT-5.6 tier for your task before it runs, then watches your Codex session live and kills it if it goes rogue on cost, scope, or secrets.
• Airline Said No — openReceived an airline compensation claim refusal? Airline Said No explains the decision, highlights missing evidence, and helps you prepare a grounded, editable reply.
• AgriVerse — openA first-person environmental science game where students investigate evidence, negotiate with AI stakeholders, and revise decisions after seeing their consequences.
• MortalOS: Evidence That Software Can Die — openCreate once. Continue elsewhere—cryptographically verified digital life across browser loss.
• Voxa AI: Intraoperative Neuromonitoring Workflow Improvement — openWith GPT-5.6 vision capabilities, Voxa integrates report creation in parallel with its intelligence case tracking, while embedding structured learning guidance during case support.
• Future Rescue, The Forgetfulness Eliminating Learning Helper — openFuture Rescue is an AI learning companion that analyses study notes, predicts what students are likely to forget, and creates personalised rescue missions before knowledge disappears.
• OrgWiki — openTurn fragmented organizational documents into structured, trusted knowledge—with AI-powered deduplication, conflict detection, and source-backed evidence.
• ClaimDone — openTurn 1 - 3 accident photos and a short description into a reviewed claim, then watch Computer Use submit your claim in an insurer portal.
• Geometric Linguistic Transformations — openDiscover and test reusable geometric directions for negation, tense, questions, and other linguistic transformations inside transformer embedding spaces.
• Crest Invoice — openCrest Invoice helps sole proprietors and freelancers create, send, and track invoices in a delightfully easy way, free of charge.
• Supr — crowdedGive founders a small, accountable AI team that turns urgent work into useful deliverables.
• Pocket Semester — openA semester-runway budget coach that turns everyday student spending into a calmer plan through finals.
• Foxy Audit — openStop promising your AI is safe. Start proving it with cryptographic proof, not just your word.
• VibeCheck — openAI-native grading for CS courses. Students code with AI; professors get line-by-line attribution, session replay & an automated oral defense.Built with Codex+GPT-5.6. We grade understanding, not code.
• Hot Trimmer — openTurn material photos into authored trim sheets and exportable PBR maps.