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:
We don't search the haystack. We shrink it.
An AI agent that dynamically analyses, learns, and recommends products to users using multiple layers of item identification, ranking by relevance, and asking the user for clarification when needed.
Zero humans in the loop: an LLM agent that runs its own recommender-systems research cycle — hypothesis, implementation, leakage review, measurement — and beat the official KuaiRand baseline.
A local AI shopping copilot with a versioned intent ledger that removes outdated preferences and adapts recommendations when shoppers change their minds.
A shopping copilot that is stress-tested against real language (not just catalog terms), learns which questions to ask to narrow the search fastest, and diversifies recommendations for fairer coverage
Everyday social media transformations easily trick standard AI detectors. Our augmentation-hardened ResNet-18 model reliably flags AI-generated media, even under severe real-world image distortion.
An AI-image detector that compares an input against real prototypes. Our model performs excellent against multiple transformations, but needs generator specific data to scale.
One stop AI image detector
Build better checkout vision with evidence you can inspect. CheckoutCheck compares models, reviews real footage, and uses OpenCV-powered agents to flag uncertainty for human review.
An autonomous ML research agent that finds weaknesses in a recommender system, forms hypotheses, runs controlled experiments, and learns from both successful and failed results.
An LLM-driven agent that autonomously writes, runs, and debugs its own code to improve a recommender ranking model — reading its own errors, banning failed approaches, and iterating without human help
Harness buddy automates all the ML research for you. It writes training code, reads its own crashes, and critiques itself when stuck. Beat the FM baseline on hidden test. Zero human interventions.
ShopMate — the shopping agent that knows when to ask and when to answer.
Conversational search that learns what matters and finds the right product faster
The copilot that tunes itself to any machine and pins the right product at #1.
Tiktok TechJam Track 4, running an AI shopping agent
An agent with 4 characters that improves Machine Learning models on its own. It works out what is actually wrong, writes the code to fix it, then checks whether the fix really did what it promised.
A shopping agent that treats changing your mind as a first-class event. Finds a shopper's exact product in under 3 turns even when the network dies.
A voice-first shopping assistant that remembers your preferences and finds the right products through hybrid AI search.
An autonomous LLM agent that runs the full ML research loop end to end on a recommender benchmark: EDA, literature and web search, hypothesis, code, train, evaluate, reflect. No human in the loop.
A private, offline-first shopping agent that understands evolving needs, adapts when shoppers change their minds, and finds the right product faster.
A conversational shopping agent that remembers what users want, reject, and change—then combines lexical and semantic search to find the right product within ten turns.
EurekaML is An autonomous ML scientist that turns hypotheses into experiments, learns from every result, and evolves its own research strategy.
The National Archives holds 34 million records. Most handwritten pages were never transcribed, so nobody can find them. Longhand reads one, asks what it cannot settle, and refuses to write unproven.