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:
Document your tennis serve, track your progress and improve your game.**
A WebMCP-powered racing strategy game where humans and AI share the pit box—analyze live race conditions, make strategy calls together, or hand the race to an AI Crew Chief.
WatchDAWG detects AI-generated images even after blur, compression, or resizing — training on corrupted images lifted worst-case accuracy from 63% to 83%.
Agent middleware that assumes the injection works and makes the payload impossible: capabilities instead of text-derived authority, unlaunderable taint, tamper-evident audit. 23/23 attacks blocked.
A transformation-aware detector that identifies AI-generated images after compression, blur, cropping, resizing, noise, and colour edits.
Robust AIGC Image Detection Point it at a folder of images. You get back a JSON file with a score from 0 to 1 for each one, where 1 means almost certainly AI-generated.
Our AI-image detector looks 98% accurate on paper. Dig into one generator and it drops to 54%. We measured that gap instead of hiding it, and built the tool that finds it.
AI agents and custom GPU kernels accelerate Transformer inference by 3.9x on an RTX 4070 with bitwise-identical outputs.
A deterministic, mathematically-bounded e-commerce agent that eliminates LLM hallucination and slashes Mean Turns to Completion (MTTC) by 25%
An autonomous ML research agent that experiments, learns from failures, and improves recommender systems with minimal human intervention.
AI shopping copilot using intent routing, conversational memory, hybrid retrieval and semantic reranking to find the right product faster with fewer turns.
AI generated content detector
The autonomous machine learning agent researches the best way to train models for recommender systems. It has tools to search, experiment, evaluate, and log its findings.
Agentic workflow for RecSys enhancement for MLE's.
A local-first conversational shopping agent that tracks changing intent and finds the right product earlier.
Spots AI-generated images even after the internet has chewed them up. Point it at a folder and it scores every file, offline, with the false-positive rate calibrated so real photos aren't accused.
Robust detection of AI-generated images under real-world transformations.
A shopping copilot that knows when not to answer.
An autonomous ML-research agent: +0.0040 over baseline, 45 runs, $2.55, zero interventions
An adaptive shopping agent that turns evolving conversations into structured intent and asks the question that reduces uncertainty fastest.
An offline, evidence-aware conversational shopping search agent that follows evolving intent and constraints to surface the right product faster.
Shopping Copilot is a headless conversational product-search Agent that turns a static query into a shopping process users can correct, built for the TikTok TechJam 2026 Shopping Copilot challenge.
We're the best!
Shopping at the speed of conversation.