Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
CourtIQ is a basketball analytics prototype that investigates whether defensive pressure and shooter movement at shot release improve field-goal outcome prediction beyond basic shot characteristics.
StreetMend tests proposed city changes, detects broken journeys to essential services, and verifies whether network repairs or new facilities would restore access.
An end-to-end machine learning pipeline and interactive Streamlit dashboard forecasting hourly urban electricity demand in Pakistan using historical consumption and weather data.
Six questions, no lab test: an explainable, bilingual (English and Urdu) AI screen that tells you whether to get a diabetes blood test, and shows exactly why. Runs fully in your browser.
LLMBoost benchmarks quantisation and speculative decoding on your own GPU, showing real speedups with confidence intervals and testing the research formula against what you get.
Climate risk you can prove — open rainfall data, explainable SRRI scores, and tamper-evident provenance for Bangladesh's Surma–Kushiyara basin.
"Solving [insert specific problem, e.g., real-time safety monitoring / defect detection] by uniting OpenCV’s powerful image processing with AWS’s cloud intelligence."
Turn English and Chinese course notices into reviewed tasks and realistic daily plans, using local machine learning without uploading your notices.
MalariaScope: snap a slide, AI spots the parasites, the technician verifies, density appears. Faster, reliable, honest malaria diagnosis.
Turning Spending Data into Smart Decisions
A coding agent that extends an animation language: Nemotron writes new motion verbs and their tests, runs them in Token Factory Sandboxes, watches the motion with a vision model, and ships a plugin.
An inspection loop where the camera moves because of what the pixels say: ArUco homography, NCC part checks, Otsu residuals — too dark or blurred, the agent repositions and re-measures.
AI computer vision spots ocean ghost nets from drone feeds, models 48h drift vectors using ocean current physics, and auto-mints geofenced Web3 smart contract bounties for fisherman retrieval.
Saving the damsels/dudes in distress at concerts, live events and festivals from cardiac arrest and heat strokes. MoshSpot sees someone go down in a dense crowd and calls the nearest EMT to them.
Watch your algorithms come to life. CodeVIZ’s custom-trained Nemotron models generate real-time visualizations of data structures, debug errors, and write code, all on Nebius.
A river changes between the places it is sampled. RiverEtch shows where, from satellite images, and backs every reading with a public record anyone can check, so you can stand behind the data.
Empowering early detection through deep learning and ultrasound.
visualize and understand Visualize how AI remembers—explore Hopfield networks, Boltzmann sampling, and quantum memory recovery in interactive 3D.
AAMS-X is an explainable AI system that intelligently schedules RF spectrum scans using Thompson Sampling, associative memory, and information gain to improve sensing efficiency using real radio data.
Manual infant length readings are error-prone. NDM Vision uses an OpenCV camera node to measure length at the edge, feeding WHO z-scores and a cloud telehealth dashboard for remote clinicians.
Offline AI that detects dashcam collisions with YOLO, narrates scenes via local VLMs, blurs faces/plates for privacy, and exports insurance-ready PDF reports — no cloud needed.
EcoBackfire finds when efficiency can backfire, using web evidence, human-reviewed parameters, falsification, and robust analysis to turn questions into transparent, reproducible results.
One OpenCV 5 engine on AWS that screens driver impairment and cognitive decline from eye signals in 80 seconds, and holds with a reason code instead of guessing when it cannot measure.
HeatShift Pakistan — Visualizing Temperature Trends and Climate Change Across Pakistan.
