Crowded

Built with typescript

2013 projects in the corpus already ship on it. Expect company.

Reviewed ideas using typescript (25 of 41)

• SlopGuard — openCodex-powered PR review that catches what only AI-generated code gets wrong: hallucinated packages, silent scope creep, and dropped auth checks.
• DeceptiForge — openDeceptiForge creates context-aware decoys across secrets, data, documents, and AI workflows—turning interactions into sensors that detect attacks, insider risk, and accidental AI leakage.
• Astral Warp Archive, Supports HoYoverse (HSR, ZZZ, GI, H3I) — open🚂🌠 Track warps, wishes, signals, and supplies across four HoYoverse titles — Honkai: Star Rail, Genshin Impact, Zenless Zone Zero, and Honkai Impact 3rd. Watch your pity climb and shine on the ranks
• PromptTripwire — openSee where Codex disagrees before it writes code—and turn hidden implementation choices into an approved execution contract.
• 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.
• Family Trip Atlas — openThe whole family is excited for a perfect vacation, its all planned out. 24 hours later, Capetown, 9am, its pouring at 10 degrees. Family Trip Atlas | Plan the whole trip. Choose what fits today.
• BioLens — openAn AI anatomy atlas that turns textbook diagrams into interactive 3D lessons. Upload an organ diagram get labeled structures rotate and explode the model and tap parts for explanations.
• 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.
• Imprint — openImprint turns any repository into a reusable Project Brain that can support Codex, Claude Code, and other coding operators without locking project context to one model or cloud.
• NOETHER — The Curiosity Engine — openLearn why AI hallucinates and how measurement catches it. Playable physics with computed black holes, a real broken benchmark, and GPT-5.6 as the map-maker, never the referee.
• 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.
• Yatra — openHistorically-grounded AI walkthroughs - RAG-backed, not hallucinated. Pick any place and era, get a narrated journey through daily life there, with generated scenes.
• Verkas HMI — openVerkas HMI turns machine specs into reviewable HMI prototypes (Industrial UIs), using AI to propose changes so engineers can create industrial visualizations in minutes rather than days.
• LitMatrix - Evidence-Aware Research Intelligence Platform — openEducation: LitMatrix maps research evidence, reveals corpus-level blind spots, and helps students and professors test stronger research directions with traceable evidence.
• 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.
• STH-Code — openSwitching from many agents is boring and not alway up to date for developpers STH-Code call the biggest agents SDK to run them into one space
• PhantomGuard - Anti-Hallucination Git Hook — openPhantom Dependency Guard scans AI-generated imports, verifies packages on npm/PyPI, and blocks commits containing phantom dependencies reducing supply-chain and dependency-confusion risks.
• 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.
• 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.
• Supr — crowdedGive founders a small, accountable AI team that turns urgent work into useful deliverables.
• ResearchAlmost AI — openResearchAlmost AI converts complex academic papers into faceless, auto-voiced short-form reels synced to a study scheduler. Consume sci-tech insights in seconds via a premium TikTok-style feed.
• Mizan — openMizan is a TypeScript-first authorization framework that adapts to your application instead of forcing a specific database schema or authorization model. Built collaboratively with Codex and AI agents