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
Ask less, find more — 3 turns to the right product out of 50,000
an AI shopping agent that asks useful follow-up questions and recommends the customer's hidden target product within at most 10 turns
Stop one dangerous agent action without killing the useful session.
Finds the exact product a shopper wants from 50,000 items in 2.06 turns, scoring 0.891 against a 0.107 baseline. Keyword retrieval and rule-based dialog state, no model in the scored path.
A zero-model, zero-token shopping agent that turns every customer reply into a hard filter — hitting the target product 99.9% of the time within ~2 turns, using nothing but standard-library Python.
From browsing to buying. In fewer turns.
vibes and more vibes
Coding agents can work together. Your agent can talk to mine, you decide what crosses.
TrueSight detects AI-generated and manipulated images using provenance, visual reasoning, and robust image classification, even after compression, cropping, resizing, or reposting.
Adaptive GPU dispatcher achieving 3.88x geomean speedup (up to 12.01x) and streaming a 20.5 TB frontier shape at 134% MFU on a single 12 GB RTX 3060.
An AI research agent that autonomously builds, tests, explains, and improves recommender systems, without leaking future data.
A transformation-aware detector that identifies AI-generated images after compression, blur, cropping, resizing, noise, and colour edits.
Your shopping assistant forgets what you said five minutes ago. Larpers Go Shopping fixes that, tracking evolving intent while never losing sight of what you're actually shopping for.
An offline, zero-token conversational agent that tracks shopper intent, asks smart questions, and ranks Amazon products with 0.96 HitRate@10 and sub-3 turn convergence.
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.
Shopping at the speed of conversation.
A privacy-conscious classroom attendance system that uses the device camera to capture a student’s face, verify identity against an enrolled photo, and record attendance in real time.
Beats the official baseline by +0.0055 (≈7σ), reproduced under fresh seeds, with zero human research decisions across 19 machine-ledgered runs — plus two original findings about agentic ML research.
Shopping search fails when customers lack the right keywords or change their minds. Our shopping agent asks smart questions, filters preferences, and intelligently ranks matches from 50,000 products.
From pixels to evidence: robust, evidence-aware AI image detection powered by a four-expert CLIP/SigLIP ensemble.
TrueFrame detects AI-generated images by fusing CLIP visual embeddings with FFT frequency signals, improving robustness to compression, blur, resizing, noise, colour shifts, and cropping.
Building a shopper agent that helps to optimise the searches for users
tjkernels: 9x velocity unleashed - Hand-crafted Triton kernels redefining transformer speed
MinionWare is a user-centric agentic AI middleware that combines orchestration, human-agent interaction, and test driven development, providing users with better results and efficient resource use.
49 – 72 of 614
