Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

OpenAI Codex

OpenAI Codex is an artificial intelligence model developed by OpenAI. It parses natural language and generates code in response. It is used to power GitHub Copilot, a programming autocompletion tool. Codex is a descendant of OpenAI's GPT-3 model, fine-tuned for use in programming applications. OpenAI has released an API for Codex in closed beta. Based on GPT-3, a neural network trained on text, Codex has additionally been trained on 159 gigabytes of Python code from 54 million GitHub repositories. You can find more information here https://openai.com/blog/openai-codex/

General
Relese dateAugust 31, 2021
AuthorOpenAI
Repository-
TypeAutoregressive, Transformer, Language model

Start building with Codex

We have collected the best Codex libraries and resources to help you get started to build with Codex today. To see what others are building with Codex, check out the community built Codex Use Cases and Applications.

Boilerplates

Kickstart your development with a Codex based boilerplate. Boilerplates is a great way to headstart when building your next project with Codex.

  • Codex Boilerplate Create a function just by typing what it should do, with help of OpenAI Codex.

Libraries

A curated list of libraries and technologies to help you build great projects with Codex.

Edit on GitHub

OpenAI Codex AI technology Hackathon projects

Discover innovative solutions crafted with OpenAI Codex AI technology, developed by our community members during our engaging hackathons.

🦷 Dental Surgical Simulator

🦷 Dental Surgical Simulator

The simulator presents a stylized, professional interface featuring a 3D viewport of a human dental arch. Users select from various surgical missions, each requiring a specific sequence of surgical steps. Success depends on selecting the correct surgical instrument and interacting with the precise target tooth at the right time. Procedural Anatomy: Anatomically accurate tooth crowns and root clusters generated via math-based geometry. Multi-Mode Visualization: X-Ray Mode: Toggles transparency of soft tissues (gums, palate) to reveal bone and roots. Wireframe Mode: Provides structural visualization of dental anatomy. View Switching: Toggle between Full Arch, Upper Jaw, and Lower Jaw views. Dynamic Theming: Seamless transition between a professional high-contrast Dark Mode and a clean Light Mode. Interactive HUD: Real-time feedback through toasts, tooltips, and a crosshair for precise targeting. Advanced Missions: Includes complex procedures like Dental Implants, Root Canals, and Bone Grafting.

Corporate Truth Terminal

Corporate Truth Terminal

Companies leave clues about their future every single day — in job postings, pricing changes, employee sentiment, and security disclosures. The challenge is that these signals are scattered across dozens of sources, and by the time most analysts connect the dots, the opportunity or risk has already passed. Corporate Truth Terminal is an AI-powered intelligence agent that solves this problem. Users simply enter a company name, and the platform continuously monitors live public web data to analyze key signals: hiring activity, financial indicators, security exposure, company sentiment, and market behavior. Instead of hours of manual research, users receive a continuously updated intelligence report generated in minutes. What sets Corporate Truth Terminal apart is its Predictive Signal Engine, which analyzes trends across multiple data sources to identify emerging opportunities and risks before they become obvious. Alongside this, Sentinel Mode detects combinations of signals historically associated with corporate distress, operational challenges, or elevated risk — giving users early warning when it matters most. The platform is built for three core audiences: go-to-market teams tracking buying intent and competitor signals, financial analysts monitoring growth trends and pricing strategy, and security professionals assessing third-party risk and exposure changes. Live web data access is powered by Bright Data's Web Unlocker, enabling reliable, real-time data collection at scale across sources protected by anti-bot systems and dynamic content. This infrastructure is what makes true predictive intelligence possible. Corporate Truth Terminal doesn't just report what companies are doing today — it helps users understand what companies may do tomorrow.

Human First Capital

Human First Capital

Finding the right people for a hackathon—whether teammates, organizers, or future hosts—is often a manual and fragmented process spread across dozens of websites and communities. This project uses BrightData's MCP to create an autonomous talent discovery agent. Instead of repeatedly searching the web myself, I provide a configuration describing the people I'm looking for, and the agent continuously gathers and evaluates candidates from across the internet. Beyond discovery, the system creates rich profiles of individuals using publicly available information. Rather than simply collecting links and social accounts, it builds a narrative around a person's work, projects, interests, collaborators, and contributions over time. This allows users to understand not only what someone has built, but also who they have worked with, what communities they participate in, and how their interests have evolved. The system learns from my feedback, improving future recommendations and surfacing people who match my interests, experience, and past hackathon projects. It can also identify past hackathon organizers and people planning future events, helping users build stronger connections within the hackathon ecosystem. Using this system, I have already discovered several impressive builders and multiple hackathons—both past and upcoming—that I likely would not have found through traditional search alone. What makes this project stand out is that it transforms web discovery from a one-time search into a continuously running, feedback-driven process. By combining autonomous web discovery, profile synthesis, relationship mapping, and personalized learning, the system acts as a persistent research partner that helps users discover opportunities and the stories behind the people creating them. The result is a continuously improving discovery engine that turns web research into an automated workflow.

EduSignal — District Root-Cause Intelligence

EduSignal — District Root-Cause Intelligence

EduSignal is an AI-powered education intelligence platform built to close the learning outcome gap across districts in India. The platform ingests evidence from news sources, government portals, NGO reports, teacher vacancy databases, community forums, and grievance portals using a real-time scraping pipeline powered by Bright Data. Every piece of evidence is classified by Gemini 2.5 Pro via AIMLAPI as Supporting, Contradicting, or Irrelevant to a root cause hypothesis. Districts are then clustered into six root cause categories — teacher shortage, seasonal migration, language barriers, infrastructure gaps, pedagogical failure, and noise — using HDBSCAN with UMAP dimensionality reduction and a RandomForest classifier with SHAP explainability. District education officers and policy analysts can explore an interactive map of India, drill into district-level evidence and feature breakdowns, compare peer districts, track live intervention effectiveness, monitor pipeline telemetry in real time via Server-Sent Events, and query an AI analyst backed by Gemini 2.5 Pro for contextual recommendations. The platform is fully production deployed — React 18 frontend on Vercel, FastAPI and Celery backend on Azure Container Apps, PostgreSQL with pgvector on Neon, and Redis on Upstash for task queuing and real-time event streaming. EduSignal turns fragmented, unstructured web data into a structured, explainable, and actionable intelligence layer for one of India's most critical public policy challenges.

Echo — Real-Time Financial Intelligence Platform

Echo — Real-Time Financial Intelligence Platform

Echo is an autonomous multi-agent financial intelligence platform built for investors and financial teams who need real-time web data to make better decisions. At its core, Echo uses Bright Data's SERP API to continuously monitor the open web — extracting news signals, hiring trends, regulatory changes, and competitive intelligence for any publicly listed company. This live web data is combined with structured financial data from Yahoo Finance and deep analysis from multiple specialized AI agents running in parallel. Echo covers all three hackathon tracks: Track 2 (Finance & Market Intelligence): Echo delivers alternative data pipelines aggregating hiring signals, earnings indicators, and competitive pricing intelligence. Its multi-source synthesis engine combines live web signals with fundamental analysis to generate structured BUY/HOLD/SELL investment signals with confidence ratings and key reasoning. Track 3 (Security & Compliance): Echo's ComplianceAlertAgent continuously monitors regulatory changes, legal risks, and ESG compliance requirements via Bright Data, delivering structured alerts with urgency ratings to risk management teams. Track 1 (GTM Intelligence): Echo's competitive signal monitoring tracks competitor moves, pricing strategies, and market positioning in real time. Key capabilities include a Portfolio Dashboard with live signal monitoring, Signal History timeline tracking how investment thesis evolves, Stakeholder Analysis mapping supply chains and peer comparisons, ESG profiling, and full PDF financial report analysis. All signals are persisted in SQLite for historical tracking. Echo is built on a four-layer architecture: Fetch → Analysis → Synthesis → Orchestration, designed to scale from single-stock analysis to continuous portfolio monitoring.

Uh Oh!

Uh Oh!

The internet is usually chaotic. Occasionally, it is also early. Before a recall becomes official, someone is already leaving clues: a person writing “my boyfriend broke out in hives after our wedding day,” a runner wondering why their supplement made their heart race on an empty street, a review mentioning a weird smell, a broken seal, or a “nut-free” snack that suspiciously tastes like almond. To most teams, that is noise. To Uh Oh!, it is the beginning of a signal. Uh Oh! is an early-warning product safety radar for food and supplement teams. We use Bright Data to scan live public web signals across reviews, forums, marketplaces, brand pages, and product listings, then correlate them with FDA/openFDA enforcement data and CAERS adverse-event reports. AI extraction turns the messy internet into structured product identity, issue clusters, severity cues, source summaries, and recommended next actions using AI/ML API. The output is a Product Safety Case File: a source-backed packet for quality, legal, marketplace trust, brand risk, and compliance teams. Each file includes official recall correlation, CAERS signal summaries, a live web evidence wall, since-last-scan deltas through Cognee memory, and a transparent 4-factor risk score across regulatory, adverse-event, live-web, and credibility signals. When the evidence reaches “Review Needed,” Triggerware opens a quality review case so human teams can investigate faster. Uh Oh! is not a public frenzy enterprise. It does not decide whether a product is unsafe, and it does not pretend that reviews, forums, or CAERS reports prove causality. It is a responsible triage layer for the moment before the obvious, when the internet is saying, “something might be wrong.” Our demo shows the most valuable moment: a product that is not officially recalled yet, but whose live web signals are starting to look like risk. We’re doomscrolling the internet so product safety teams don’t have to.