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
A small team of Computer Engineering students from the College of Alice & Peter Tan in NUS trying to get employed.
Bouncer enforces real, server-side authorization on every Agent action even blocking the Agent itself when manipulated into reaching for another user's data. 'Not your Agent' is actually enforced.
The best optimized GPU Kernel for a transformer layer
Robust Detection of AI‑Generated Images Under Real‑World Transformations
A lightweight conversational shopping agent that turns evolving customer preferences into fast, accurate product recommendations, entirely offline.
Drop-in PyTorch Transformer layer for Track 3: 1.92× geo-mean speedup, strict state_dict, 932× under tolerance. Shape 14 completes in 5 GB; the reference cannot run (18 TB score tensor per layer).
Shape-aware Transformer optimization delivers a measured 4.98× geometric-mean speedup across 13 test shapes and validates full 100,000-token sequences on an H100 GPU using independent accuracy checks.
ShopScout: A zero-cost, offline-first conversational shopping agent combining 6-route hybrid retrieval and atomic state tracking to surface target products in just 2.3 turns.
TrippyShoppy is a deterministic, offline-first conversational shopping agent.
Autonomous FM HPO for KuaiRand-Pure: Qwen LoRA + GP-EI (HPUCB) search lr/l2/k on date-split valid; ship valid-best test ranks. Modest gain over official FM.
A multi-turn shopping agent that combines deterministic memory, hybrid retrieval, and constraint-aware reranking to find the right product quickly—even when preferences change.
An optimized transformer layer verified on two real GPUs — three optimizations that looked safe on one backend failed on the other.
Generative AI creates photorealistic fakes at scale. Spotting them in a lab is easy. The hard part is real images get re-encoded, resized, or cropped, erasing the artifacts detectors rely on.
Giving every AI Agent only the access it needs, only for as long as it needs it.
A multi-turn conversational shopping agent that finds a customer's hidden target product inside a 50,000-item Amazon catalog, scoring 8.35× the official baseline with zero LLM calls or network access.
Added real ownership checks to the Agent platform so User A can't see or touch User B's agents - this is enforced in the backend, not just the UI.
A triple-layered security middleware for AI coding agents — smarter prompt-injection detection, a confirm-before-write gate, and one-click rollback.
Shopping copilot!
Building a conversational search system that asks smart questions and finds a customer’s ideal product from 50,000 items within 10 turns.
AI Image Detection, Built for Real-World Conditions.
Just tell us what you need. We'll figure out what you're looking for.
Autonomous ML agent that engineers causal features, tunes & blends LightGBM/XGBoost/CatBoost rankers, self-converges in 8 min, and beats KuaiRand's baseline +5.5% relative on hidden test.
We optimized a transformer layer on an NVIDIA laptop and a MacBook. Every change was correctness-checked and timed before being kept; 25 experiments, 11 rejected, 2–15x faster.
Enhancing your shopping experience
481 – 504 of 614
![ShopMind [Track 4]](https://d112y698adiu2z.cloudfront.net/photos/production/software_photos/005/215/766/datas/medium.png)
