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
An adaptive shopping copilot that understands changing intent, remembers preferences, and combines keyword, semantic, and constraint-aware search to find the right product in fewer turns.
An Neural Network powered AI Image detector
It might know you better than you know yourself.
ZZZ
Give it a dataset and a metric: it hypothesises, writes the code, trains, measures, and keeps only what replicates. Beat the KuaiRand baseline in 12 iterations, no human in the loop.
Autonomous agent that proposes, runs, and scores its own recommender-model changes.
Find the right product, one useful answer at a time.Seekly listens for what matters, adapts when intent changes, and shows the evidence behind every recommendation.
An offline multi-turn shopping agent that updates preferences, asks smart follow-ups, and ranks products from a 50K catalog.
Autonomous ML agent - Zero human intervention
DUET — Depth-Uniform Ensemble with early Terminate
TK-techjam-2026
Writes its own recommender, reads its own training logs, and fixes its own bugs — unattended.
Robust detection of AI images in real time as you browse social media
An AI stylist that recommends perfect outfits based on occasion and budget.
Finds the right product in 3.3 turns with zero tokens, zero network, and no LLM. Deterministic retrieval plus one well-chosen question. 8× the organizer baseline.
An offline conversational shopping agent that tracks evolving intent, handles changing preferences, and ranks the right products from 50,000 catalog items in fewer turns.
Katsu is a lightweight hybrid model for detecting AI-generated images, designed specifically for real-world redistribution, where images may be recompressed, resized, cropped, or affected by noise.
Ctrl Alt Del turns opaque Agent execution into an auditable run so as to protected by prompt security, durable memory, Glass Box tracing, and estimated-versus-actual cost evidence.
EntroShop: tree-guided shopping copilot that narrows 50,000 products to the one you meant in 1.6 turns, the way binary search narrows a sorted array.
E-commerce matches keywords. I built a shopping agent that finds the product by asking the right question and matching the shopper's words. 96% hit rate, 2.6 turns, TechScore 0.84, offline and free.
A conversational product recommendation system which is like a shopping assistant. Understands user’s intent, keeps track of session state, and asks follow-up questions before recommending products.
Middleware for autonomous AI agents, providing secure execution, permissions, observability, multi-agent coordination and human control, so agents remain powerful, safe and manageable.
An AI shopping copilot with fast deterministic reflexes, autonomous LLM reasoning, and a confidence controller for hard conversations.
A CNN detector trained on 20 generators and stress-tested across 13 degradations. Learned features lose 0.09 AUC under compression and blur. Hand-crafted frequency features lose 0.24, below chance.
553 – 576 of 614
