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.

Order Block detector with LLM advice

Order Block detector with LLM advice

This implementation demonstrates the successful integration of a 120 billion parameter Large Language Model (LLM) hosted on AMD Cloud with an algorithmic trading system based on the Order Block strategy. The LLM acts as an expert consultant that validates and optimizes trading decisions in real-time. The use of **AMD Cloud GPT OSS 120B** brings an advanced artificial intelligence layer to the trading bot, enabling more nuanced and contextual decision-making than traditional algorithmic rules. ### Key Features - Real-time signal validation by 120B parameter LLM - Expert reasoning for each trading decision - Automatic fallback if LLM is unavailable - Complete logging of LLM consultations - Configurable confidence thresholds

AlphaTrading

AlphaTrading

AlphaTrading is a multi-agent AI trading framework designed to bridge advanced off-chain quantitative analysis with verifiable on-chain execution. Built from first principles, it moves beyond simple single-prompt wrappers by introducing a collaborative "AI Syndicate" architecture. The system leverages LangGraph to orchestrate a multi-stage workflow. Specialized AI analysts (Market, News, and Quant) process cross-domain data signals, which feed into a rigorous Bull/Bear research debate. This ensures every strategy is deeply stress-tested before a Trader agent generates a preliminary TradeIntent. A critical technical differentiator of this framework is the strict decoupling of AI reasoning from financial execution. To ensure capital safety, a deterministic Risk Engine intercepts all AI-generated proposals. It enforces hard constraints—such as maximum position sizing and single-order limits—before any action is finalized. Furthermore, the system maintains a continuous learning loop, utilizing ChromaDB for semantic memory and SQLite for robust portfolio state tracking. To solve the "trust black box" inherent in autonomous AI, the framework natively integrates with the ERC-8004 standard. The agent registers a verifiable on-chain identity, signs trade intents using EIP-712, and interacts with a smart contract RiskRouter. By waiting for asynchronous on-chain feedback to update its virtual ledger, the agent creates a transparent, immutable track record, building a measurable reputation based entirely on objective, risk-adjusted performance.

AutoHedge AI

AutoHedge AI

AutoHedge AI is an autonomous multi-agent crypto trading system designed to operate as a trustless financial agent. The system continuously analyzes live market data from Kraken, computes technical indicators such as RSI and moving averages, and combines multiple strategy agents including momentum, mean-reversion, and trend-following to generate deterministic trading decisions. A risk management layer enforces drawdown limits, position controls, and execution safety before any action is taken. Each decision is converted into an EIP-712 structured trade intent and cryptographically signed by the agent wallet, ensuring that actions are verifiable and tamper-proof. The agent maintains an ERC-8004 compatible identity and produces validation artifacts for strategy decisions, risk checks, and execution checkpoints. These artifacts include hashes and metadata that provide a transparent audit trail of the agent’s behavior. The system runs autonomously in the background, periodically scanning markets, generating decisions, and updating portfolio state without manual intervention. A React dashboard visualizes the agent’s identity, latest decisions, indicators, signed intents, trade history, and reputation metrics. AutoHedge AI demonstrates a complete trustless trading workflow combining Kraken market integration, deterministic AI decision-making, EIP-712 signed intents, and ERC-8004-compatible validation and identity infrastructure.

Vartovii Sentinel-8004

Vartovii Sentinel-8004

`Vartovii Sentinel-8004` is a trust and control layer for autonomous trading agents. Instead of building another trading bot, we focused on the checkpoint that should exist before capital moves. Each trade starts as a canonical `TradeIntent`. Sentinel evaluates that intent against deterministic risk policy and returns one of three machine-readable outcomes: `ALLOW`, `DENY`, or `ALLOW_WITH_DOWNSIZE`. Every decision produces a signed verdict, validation artifact, permit verification result, and Kraken-shaped execution preview so judges can inspect the full proof chain end to end. The public repo implements real EIP-712 typed-data signing and verification, ERC-8004-style identity binding, organizer-aligned shared Sepolia contract configuration, and a hosted judge-first walkthrough with four canonical scenarios. The main demo surface is intentionally narrow: judges can open `/judge` for the proof story or `/operator` for a dry-run pipeline without needing private infrastructure, exchange credentials, or hidden services. This is the primary judged product surface. A separate founder-run companion repository exists only as supporting proof that the guardrail also matters in a live-market loop. As of April 8, 2026, that founder-run companion log contains 130 recorded cycles, including 83 approved shared-Sepolia RiskRouter actions. The public submission does not depend on that companion surface to run. Sentinel-8004 fits the hackathon thesis because it combines AI-agent execution intent, cryptographic verification, risk controls, and transparent auditability into one reusable control layer. The long-term product path is a deployable guardrail module or micro-SaaS for autonomous trading systems, treasury agents, and policy-constrained execution workflows.

Ghetto-Bird Ai Pet

Ghetto-Bird Ai Pet

Ghetto-Bird AI Pet is an AI-powered virtual companion inspired by the creativity, resilience, and culture of urban communities. The project reimagines the digital pet experience by combining conversational AI, personality modeling, and adaptive learning to create a dynamic companion that evolves with its user. Unlike traditional virtual pets, Ghetto-Bird AI Pet is emotionally responsive and culturally aware. It learns from interactions, develops preferences, remembers conversations, and adapts its tone and personality over time. The AI pet can offer motivation, storytelling, humor, life advice, and entertainment, creating a personalized experience for each user. The project aims to make AI companionship more relatable and expressive by blending culture, technology, and emotional intelligence. Whether users are looking for a friend, a hype partner, or a daily check-in companion, Ghetto-Bird AI Pet grows alongside them — becoming smarter, more intuitive, and more uniquely theirs over time.

TradeWise AI

TradeWise AI

Traders face information overload and emotional bias when making market decisions. TradeWise AI addresses this by combining automated technical market intelligence with behavioral insights and social content generation. The platform computes indicators (SMA, RSI, ATR, momentum), identifies patterns, and produces clear, human-readable explanations. It analyzes trader behavior—win rate, holding time, trade frequency—and provides psychology-driven recommendations and trade recovery probabilities. TradeWise AI also includes a RAG-backed search, on-demand content creation for social platforms, real-time alerts, and demo/offline modes for safe exploration. Built as an MVP, it’s aimed at retail traders, trading coaches, and small teams who want actionable analytics, better discipline, and shareable market narratives—while emphasizing education and sound risk management rather than guaranteed predictions.