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:
You say you'll do something. The cameras confirm you did.
Single-Pass Drone Video to Accurate 3D Model Generation System AI-Enabled Georeferenced 3D Reconstruction from a Single UAV flight
Weather is wiping names off gravestones. Ghostlight rebuilds worn stone in 3D, and a Nemotron agent reads it, checking every guess against the carving and real records. Nothing invented.
AI that learns with the tools every robotics programmer knows: PID, LQR and GVF drive a VEX robot, a residual network refines them, and NVIDIA Nemotron on Nebius plans the match.
An agent that measures a wound from a phone photo with OpenCV 5 on AWS, checks its own outline, coaches a better photo, catches a misprinted card, and asks a nurse when healing stalls.
Supercharging Nemotron inference: 2x faster, 60% leaner, zero quality loss.
Dashcam video → OpenCV 5 measures every pothole in m² → an AI agent drafts repairs → a human approves → the next drive verifies the fix. Live on AWS with Amazon Nova.
RADvê combines computer vision, AI and adaptive reinspection to monitor personal dosimeter use, assess visual evidence over time and support safer, human-supervised radiation protection.
An autonomous OpenCV 5 (dnn5 + AWS COOL) 3-plane Knee MRI agent (0.957 RSNA LB) that sees across 144 slices, reasons over Cleanlab radiologist blind spots, and acts via 1.65× Lanczos4 focal zoom.
See a whole camera-trap video at once: OpenCV 5 traces every animal visit through a 3D block of the clip, so you know what came, when and for how long without watching the footage.
Match analysis for Nigerian clubs with no analyst: a coach report from a fixed 3-camera rig, plus OpenCV 5 on AWS turning each moment it flags into watchable video.
Emergency care moves faster than documentation, leaving critical details behind. Resona turns spoken care into a clear, evidence-linked timeline with a handoff report so medics can focus on patients.
Replay the photos you've already posted and watch an AI geolocator close in on your neighborhood, see exactly which photos give you away, and get the smallest fix that pushes it back out.
One search map for drones, ground teams and the radio. NVIDIA Nemotron on Nebius Token Factory reads the photos and voice reports and proposes where to search next; a person approves.
Illumination-aware lunar image registration that aligns the Moon’s surface across extreme changes in lighting, viewpoint, and scale.
OpenCV 5 turns station video into zone density and crowd-turbulence readings, applies explainable safety rules, and recommends actions for a human controller to approve before a crush develops.
An OpenCV 5 and AWS-powered autonomous vision platform that predicts wildfire risks, detects early ignitions via drones, and orchestrates real-time tactical dispatch.
POLARNAV AI combines AI and satellite imagery to detect and track Antarctic icebergs, assessing risks for safer navigation in icy waters.
Edge-vision AI waste classifier guiding consumers to the right municipal bin with instant visual recognition and actionable disposal rationale.
Our hack: prove an agent can teach a small model one job, test it on tickets it never saw, and ship it only if it wins, all on a $1 budget.
Drone photos and radio reports in, where to search next out. OpenCV 5 finds people in search-and-rescue photos, an agent proposes the next move, and a person approves every one.
AI-powered brain MRI analysis system built with PyTorch/OpenCV that detects potential tumors, visualizes predictions using Grad-CAM, and evaluates image quality and model reliability
Turn product photos into reviewed stock updates and smarter shopping.
The future of compute is in creating personalized solutions for people. Avatar is the tool that will kickstart digital twinning, starting with digital avatars for user manipulation.
