Top Builders

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

OpenAI's Assistants API

OpenAI's Assistants API simplifies AI integration for developers, eliminating the need for managing conversation histories and providing access to tools like Code Interpreter and Retrieval. The API also allows developers to integrate their own tools, making it a versatile platform for AI assistant development.

General
AuthorOpenAI
DocumentationLink
TypeAI Assistant

Model Overview

The Assistants API enables developers to create AI assistants using OpenAI models and tools. It supports various functionalities such as managing conversation threads, triggering responses, and integrating customized tools.

Assistants API Tutorials

Technology Resources

The Assistants API allows developers to construct AI assistants within their applications. An assistant can leverage models, tools, and knowledge to respond to user queries effectively. Presently supporting Code Interpreter, Retrieval, and Function calling, the API aims to introduce more tools developed by OpenAI while also allowing user-provided tools on the platform.

To explore its capabilities, developers can use the Assistants Playground or follow the integration guide in the official documentation. The integration process involves defining an Assistant, enabling tools, managing conversation threads, and triggering responses.

Edit on GitHub

OpenAI Assistants API AI technology Hackathon projects

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

Doen AI

Doen AI

Doen AI is a real-time AI guidance system designed to transform how humans perform skilled physical work. Using a small wearable camera, our AI sees what the worker sees and provides step-by-step instructions, from identifying worn parts to guiding precise actions, reducing months of training to minutes. The system is ideal for industries like field services, manufacturing, healthcare, and construction, where skilled labor shortages are a critical problem. By combining multimodal AI, computer vision, and AR-enabled devices, Doen AI empowers workers to learn on the job, improve efficiency, and maintain high-quality standards, all while ensuring safety and scalability.

RescueRoute AI - Autonomous Disaster Response

RescueRoute AI - Autonomous Disaster Response

RescueRoute AI is an autonomous disaster response coordination platform that combines real-time simulation, AI-driven command decisions, and fleet monitoring to optimize emergency response operations. The system features: - Multi-robot fleet simulation with A* pathfinding for obstacle avoidance - Real-time data streaming via Server-Sent Events (SSE) for instant dashboard updates - AI-powered strategic decision-making using Google Gemini to prioritize missions and manage battery constraints - Automatic battery management with intelligent charging station routing - Production-ready architecture with proper state management, CORS security, and structured logging Built during the 48-hour hackathon using FastAPI (backend), Next.js 16 + React 19 (frontend), and Google Gemini AI. The simulation engine manages 5 autonomous robots across a 50Ɨ50 grid with obstacles, charging stations, and mission priorities. The architecture is designed to scale from disaster response to warehouse automation and urban logistics scenarios. Tech Stack: FastAPI, Next.js, TypeScript, Tailwind CSS, Google Gemini AI, Docker Compose

SANCTUMSIM

SANCTUMSIM

SANCTUM-SIM is a simulation-first robotics platform that demonstrates autonomous infrastructure management under real-world constraints. In a simulated geothermal and logistics facility, mobile inspection and maintenance robots operate in dynamic heat zones, energy limits, and failure-prone environments. Unlike scripted demos, each agent continuously evaluates tradeoffs between energy use, time, and operational risk using cost functions and a planner-based decision engine. Every action generates a structured, explainable rationaleā€”showing why a robot rerouted, delayed, escalated, or conserved power. The system introduces sensor noise, randomized failures, and environmental volatility to demonstrate robustness, recovery, and graceful degradation. A browser dashboard visualizes agent states, decisions, and performance metrics in real time. SANCTUM-SIM enables energy operators and infrastructure teams to simulate, validate, and build trust in autonomous systems before real-world deployment.

SentinelOps AI Autonomous Robotics Engine

SentinelOps AI Autonomous Robotics Engine

SentinelOps AI is a simulation-first robotics platform designed to demonstrate how autonomous systems reason, decide, and adapt in dynamic environments. The platform combines a robotics state simulator, an AI-driven decision engine, and structured event logging into a modular backend architecture built with FastAPI. Each simulation step updates the robotā€™s state, generates events, and triggers an AI reasoning loop that selects the next optimal action with confidence scoring. All decisions and events are logged for traceability, auditability, and system analysis. The goal of SentinelOps AI is to bridge the gap between artificial intelligence and robotics by showcasing clean API design, scalable backend structure, and autonomous control logic in a production-style system. The project emphasizes transparency, modularity, and intelligent automation as foundations for next-generation robotics platforms.

CarphaCom - Robotised E-commerce

CarphaCom - Robotised E-commerce

CarphaCom is a revolutionary "Shop-to-Ship" platform that bridges the gap between digital sales and physical logistics. Built for the 2026 enterprise landscape, it uses Medusa.js 2.0 and Next.js 14 to provide a lightning-fast, multi tiers pricing B2B/B2C experience. The core innovation is the seamless integration with NVIDIA Isaac Sim hosted and Vultr infrastructure. When a customer places an order on Frontstore, a real-time event triggers an autonomous robot in our Digital Twin warehouse wich will fulfill the order by picking from the Shelfs (Categories) the product, will take the products to Packing zone then to the Courier zone to be picked up and delivered to customers, the robot will automatically mark the order in Medusa as completed and put the Couriers Tracking number, and automatically will be generated a PDF/XML invoice. Using Gemini AI, users can also interact with the fleet via voice using the Tab AI from Warehouse and push MIC and speak then push to MIC to end, the integrated Gemini will take the command and give to the robots which will execute commands, or chat to manage inventory, the inventory are the categories and products from the Frontstore/Medusa. The robot autonomously picks, packs, and moves the product to the courier station. Once the physical task is completed, the robot updates the digital store status to "Ready for Pickup" automatically. CarphaCom also includes advanced business tools: Professional Dashboard, Google Merchant Center, Analitycs, Console sync, Google Login, AI-powered autoblogging using Gemini model, CMS, B2B API SYNC, XML/CSV bulkt guided importation, Integrated PayU, proxy+contact scrapping, google maps api for contacts, and sms+email campaigns. It is a complete, scalable, and autonomous commerce solution designed to eliminate human error and maximize efficiency. Without the warehouse robotised integration the E-commerce it is at 75% of being complete needing hardening, testing and releasing a stable version.

Warehouse Orchestrator AI

Warehouse Orchestrator AI

Warehouse Orchestrator AI is an AI-powered warehouse automation simulation platform designed to demonstrate how autonomous robots can optimize modern logistics operations. The system simulates a real warehouse environment with multiple zones (A, B, C, D, Packing, Charging Dock) where robots intelligently navigate, avoid obstacles, and complete delivery tasks. The platform includes a futuristic SaaS dashboard that provides real-time monitoring of robot status, battery levels, active tasks, performance analytics, and system logs. It showcases intelligent routing and decision-making logic that can scale to real-world warehouses. This project is built using HTML5 Canvas, JavaScript, and CSS, optimized for smooth real-time rendering, and deployed on Cloudflare Pages for fast global access. The architecture is designed to be cloud-ready and extendable for integration with Vultr infrastructure and real robotic systems.