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:
Offline conversational product search that asks, remembers, and reranks across turns.
A shopping copilot that uncovers hidden needs from conversation, adapts when preferences change, and explains every recommendation.
Conversational search engine built with an AI embedding model with no external API calling
EpsilonRec is not one recommender model, but an autonomous ML researcher that hypothesizes, trains, evaluates, and revises KuaiRand-Pure recommenders with zero human intervention.
An LLM-driven research harness that edits, evaluates, and reverts a from-scratch NumPy Factorization Machine, discovering a statistically verified within-user ranking improvement on KuaiRand-Pure.
A deterministic, fully-offline conversational shopping agent that finds the exact product in under 3 turns — 7.7× the official baseline, zero LLM tokens.
An autonomous ranking agent that tests ideas across time, rejects fragile gains, and preserves reproducible evidence.
AI-image detection in your browser that adapts to JPEG, noise, blur, resizing, cropping, and the distortions introduced when images are reposted.
Collaborate with your AI agent to print beautiful, minimal thermal receipts – send a prompt or voice chat, then watch as your agent drafts in the browser, iterates with your help, and prints
Embedflix: An autonomous ML research agent that iterates on a video recommender system: researching techniques, writing code, training models, and improving ranking quality without human intervention.
Agents Pass what They Learn. Nothing Passes Unwatched
An autonomous ML research agent. It verifies its own results instead of trusting them, and beats the baseline where a greedy agent scores below it.
An auditable autonomous ML research loop that iterated from the officialKuaiRand-Pure FM baseline to a validation-selected DIN-lite/FM rank ensemble.
Your lens for digital authenticity
An autonomous ML research agent for recommender systems that tries to disprove its own findings. It found a +0.0314 result, proved it was worth +0.0023, and reported the smaller number.
A robust AI-generated image detector combining multi-layer visual representations with forensic frequency and artifact features to generalize across unseen generators and transformations.
Cereal Crunch is a binary AI-generated-image classifier (<2B parameters) that provides detection on both clean images as well as on images under six post-processing image transforms.
A reproducible parameter ensemble for AI-image detection that stays robust under JPEG, blur, resize, noise, color jitter, and crop.
We built a 21.7M-parameter ViT detector for robust AI-image detection, scoring 0.9362 across unseen generators, with deployment via Chrome extension and future TikTok integration.
No Cost high-precision conversational e-commerce search delivering 98% hit rate in under 3 turns at sub-50ms latency.
An autonomous ML scientist that safely proposes, tests, diagnoses, and preserves recommendation-model improvements for KuaiRand-Pure.
The harness measures; the agent decides.
PC cleaners find "1,248 problems". Chatbots don't have the right tools to look inside your PC. PC Agent does: NVIDIA Nemotron measures your PC, explains the real cause and proves every number.
Hand-written Triton attention kernels, benchmarked against the baseline, with shape-aware dispatch choosing the fastest path per case with every optimization validated and explainable.