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:
From Sentinel-1 radar to cut-off villages: maps flood and debris, flags buildings, roads and bridges in the flood zone, ranks who to reach first, and writes a situation report in English and Nepali.
Rostrum turns speech delivery into measurable evidence, detecting exactly where a speaker rushes, hesitates, or loses emphasis with timestamped, explainable acoustic analysis.
AI-powered 3D coronary digital twin with explainable per-vessel risk estimation.
All-weather satellite radar (Sentinel-1 SAR) & AI copilot to map flood extents, detect severed bridges, and identify cut-off villages from space.
SpeechFlaw turns speech coaching into data science—aligning your audio against master orators to ground cadence, pitch, and vocal flaws with millisecond precision and 0-100 rubric scores.
CardioTwin: a beating 3D heart that predicts coronary artery disease and which arteries are narrowed from routine tests, showing the evidence behind every number. Research prototype.
Describe your business. Tavily finds the news that hits it, Nemotron proposes plans, and a simulator tests every plan in several futures. You get a decision memo with sources.
ECHO : An explainable AI system that pinpoints speech delivery flaws, explains why they occur, and provides objective, timestamped feedback through contrastive audio analysis.
Kanopy measures how much forest a reserve holds and how fast it is being lost, from open satellite data, then anchors every figure on-chain so anyone can recompute and verify it.
Accessible contactless vital monitoring that democratizes cardiovascular health screening for underserved communities using standard camera sensors.
Hear exactly where a delivery goes wrong, why, and what it sounds like fixed.
Evidence-grounded speech evaluation with acoustic signal grounding, millisecond flaw timestamps, reproducible 0–100 rubric scores, and contrastive matched-pair analytics.
Train how you speak; measure how you deliver. Mock interviews, news reading, debate and storytelling, scored on pace, pitch, pauses and filler words.
Turn every speech into measurable progress with timestamped delivery insights, acoustic analysis, and actionable coaching.
Turn vague speech feedback into measurable evidence. Compare two readings, pinpoint differences in pauses, pace, and energy, and replay flagged moments—all locally, with transparent scoring.
Coronary risk, mapped to the heart: per-vessel CAD prediction on an interactive 3D heart, with SHAP explanations, uncertainty and an honest "uncertain: refer".
Turn satellite change into auditable flood evidence: native radar and optical maps, explicit unknowns, and road-access proofs that show which route conclusions survive uncertainty.
Radar satellites map a Himalayan flood through monsoon cloud, then answer the question that moves rescue teams: which villages just lost their road to a hospital, and which bridge fails next.
Hear the difference. See the evidence. Browser-local AI turns same-transcript speech comparisons into timed, explainable practice feedback—with a 90-case dataset and transparent evaluation.
An AI agent that uses a computer the way a real person does: human mouse movements, typing with typos and pauses, reading, browsing and writing documents.
Compares your speech to a reference recording, finds timestamped flaws in pace, pitch, pauses, and volume, and explains each with real numbers and coaching tips.
A coding agent that finds silent bugs placing medical scans in the wrong spot, fixes them with NVIDIA Nemotron on Nebius, and proves each fix in millimetres against physical ground truth.
SvaraTrace compares reference and candidate speech, analyzes acoustic features, identifies potential delivery flaws, and explains measurable differences with actionable feedback.
🎙️ Meet VoxContrast: AI that catches speech flaws, pinpoints when they happen, and turns every “um” into an opportunity to improve! 🚀✨
