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:
Szpont AI
An AI-powered career path finder that analyzes your skills, interests, and trends to recommend personalized career paths, required skills, and step-by-step roadmaps for success.
Preventing the next aviation tragedy by making sense of the signals hidden in plain sight
2-Stage Neural Compression Pipeline
Sustainable procurement shouldn’t be guesswork.
An interactive atlas that shows where tree planting can most reduce urban heat exposure using heat, tree, and demographic data.
Team name : Give us internship Takes scanned document images and automatically extracts their text using OCR, then compresses that text using Adaptive Huffman encoding, all in a single API call.
We teach machines to read noise and forget nothing, a CNN that deciphers corrupted digits fed into a compression engine that shrinks the output without losing a single bit.
Project consists of Neural Networks + ML algorithms to find correlation between tear drops microscopic imagery and diseases. Whole environment is packed in user-friendly GUI and fully localhosted.
Predicting diseases from a single tear. Our multimodal AI analyzes nanoscale physical structures in tear fluid from AFM scans, fusing biophysics and deep learning for >90% accuracy.
Home solar economics, decided in 20 seconds, and powered by 10 paid APIs through one Orthogonal SDK.
From Noisy Scan to Optimized Data: A High-Performance Neural Pipeline
AI that explains medical scans and surfaces clinical trials at diagnosis — replacing biased manual referrals with automated, equitable matching
An end-to-end pipeline that reads noisy scanned documents with a custom-built neural network and compresses the output using a custom Adaptive Huffman encoder; all from scratch, no external libraries.
Submission to MariHacks Math Challenge W26. Simulation of physical principles using Euler's method, representation of phase space and determining error in the methods.
Coastal water toxicity ruins harvests overnight. AquaYield fuses Scripps data into a predictive AI risk engine, giving aquaculture farms the early warning they need to harvest before disaster hits.
The ocean looks fine. It's not. Ocean Pulse sees the crisis coming before it hits the surface.
Crystal: A Hybrid AI Framework for Precision Diagnosis of Systemic and Ocular Diseases via Tear Film Micro-Analysis.
I built a prediction market trading bot combining risk-free arbitrage with an XGBoost-distilled classification model to exploit crypto market inefficiencies at each day end
The ocean is being eaten alive and nobody's watching. Aegis Ocean uses 75 years of California ocean data to detect the exact moment a marine heatwave triggers an urchin boom and risks a kelp forest.
Without Northern anchovies, the California coast ecosystem would collapse immediately. Knowing their larvae population and health is thus crucial. That's why I made a model to try and predict that.
AI-powered muscle segmentation, 3D visualization, and real-time injury prevention for physical therapy patients.
A digital platform designed to promote sustainability by making carbon credit tracking and trading transparent, accessible, and trustworthy.
Lyra enseña piano con IA: conecta tu teclado, medimos tu ejecución en tiempo real y Gemini crea ejercicios a tu medida. Libre, accesible, sin maestro requerido.
![[AIoT] [Szpont AI] System Ragnarok](https://assets.devpost.com/assets/defaults/thumbnail-placeholder-8c916ef4da99a222ce6ece077c71c7e282f071f830747b2abb5718018cbfa699.gif)
