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:
Ctrl + F for your room // Never lose anything again.
Agentic flood early-warning for Pakistan: radar AI, 2010 benchmarks and live river data feed a 4-agent pipeline that classifies risk, projects flood spread, and sends citizen and authority alerts.
AI flood early-warning for Pakistan: Sentinel-1 radar + U-Net sees through monsoon clouds, compares against the 2010 floods, fuses live river data, and triggers response alerts.
It is a project that works on agricultural areas and finds where the weed is and help it to how to remove to it
Normal CCTV records thousands of innocent students to catch one incident. ARJUN watches no one, until someone gives it a reason to.
Is that ML paper's number real? Paper2Proof re-runs the experiment in an isolated Nebius sandbox and gives you a verdict you can verify yourself.
Apertus turns plain English into safe, checked robot pick-and-place plans, and asks or refuses when it isn’t sure
Turn existing CCTV into floor measurements and reviewable forklift warnings. A vision agent checks the evidence before an alert; a simulator demonstrates automatic slowing and stopping.
Reflex compiles routine agent decisions into a calibrated, permutation-invariant fast path using nemotron based embeddings locally and calls Nemotron only for uncertainty or missing capabilities.
Transforms Sentinel-1 satellite imagery into flood maps, flags potentially damaged roads, and analyzes settlement connectivity to support faster, data-driven disaster response.
Free-satellite flood mapping that shows where a Himalayan flood reached, what it broke and who it cut off, with an AI copilot that never invents a number.
Contrastive speech coach: compares your delivery to an ideal recording, pinpoints the exact seconds that go wrong, and explains why using measured pace, pause, pitch and loudness numbers.
From satellite pixels to life-saving decisions — FLOODVISTA AI maps flood damage, detects disconnected roads, and identifies isolated communities so rescue teams can reach those who need help most.
A breast cancer patient file that keeps every test's evidence, labeled observed, inferred or hypothesis; a Nemotron agent on Nebius Token Factory writes the case note; NVIDIA FLARE trains the model.
Turn 2D Olympic broadcast footage into 77-joint 3D skeletons, classify multi-axis tricks, and predict official FIS scores using NVIDIA 3D Body Pose NIM, Nemotron-3 Ultra, and Omniverse digital twins
TRINETRA turns satellite flood candidates, unknown terrain, and mapped infrastructure into an interactive situation map, conditional settlement-access scenarios, and a one-page report for field teams.
An AI speech coach that pinpoints delivery flaws to the millisecond and plays back your own voice, corrected.
Your voice. Understood in detail.
Cadence judges your speech against every great reading of the same words, then shows exactly which words fell outside their range, with the numbers to prove it
RhetorIQ: AI-powered speech analytics that transforms delivery into measurable insights through real-time acoustic analysis and reference-based comparison.
Hear what needs work. Delivery connects speech audio with the words you spoke to pinpoint delivery differences, giving you timestamped feedback, acoustic evidence, and reference playback.
An AI-powered platform that detects floods using satellite imagery, forecasts risks, maps affected communities, and visualizes real-world flood impacts through interactive 3D maps and early warnings.
An OpenCV 5-powered AI platform for accurate solar cell defect detection, visual inspection, and cloud-based analysis using AWS.
We dont care about money, we save lives!
