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:
Multi-Turn Shopping Copilot for Catalog Findability
Raiding the fakes real-world edits couldn't hide.
A closed-loop AI agent on Google Cloud that investigates data incidents, generates schema repairs, validates them in a sandbox, and prevents downstream ML system failures.
Compression and reposting change an image's pixels but not its origin. We fine-tune a vision encoder so its features ignore that damage, and detection accuracy holds where it usually drops.
An autonomous ML research agent for recommender systems. It forms hypotheses, patches its own code, executes iterative optimization loops, and verifies results via bootstrap on sealed splits.
tiktoktechjam - shopping copilot
We built a hybrid detector (CLIP + frequency analysis) that catches AI-generated images even after blur, compression, resizing, or noise -- the stuff real images actually go through.
An autonomous agent that does ML research: hypothesise, code, run, measure, repeat. It beat the official KuaiRand recommender baseline in 30 self-directed iterations with zero human intervention.
An offline-first conversational shopping agent that turns changing preferences into fast, explainable, catalog-valid recommendations—without network calls or model tokens.
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.
A transformation-aware AI image detector that combines semantic and forensic evidence to remain reliable after compression, resizing, and real-world image transformations.
Autonomous agent that proposes, runs, and scores its own recommender-model changes.
An LLM agent that autonomously runs the ML research loop on KuaiRand-Pure: observe, diagnose, invent, implement, verify, decide. Beat the official baseline in 374 experiments, unaided.
We created a code! Draw dots on a box with any marker. OpenCV reads the code off raw cardboard in real time, so you secretly know what's inside. :). No printing nor labels all too easy. All too CV.
Detects AI-generated images using semantic, edge and frequency clues, built to withstand common edits and generalise to unseen generators.
An autonomous ML research agent for KuaiRand-Pure that proves its improvements. A paired-seed bootstrap gate rejected five hypotheses and accepted one — numpy only, zero GPU, zero LLM tokens.
An autonomous ML research agent that runs the complete engineering loop on KuaiRand-Pure which reads the problem, trains, evaluates, and iterates with zero human intervention during runs.
An autonomous AI SRE that diagnoses and fixes production incidents in minutes, with a human approving every fix. Six agents, multimodal Gemini, live on Google Cloud.
Project Varuna is an AI-based decision support tool that makes predictions about water quality based on environmental data and explain these predictions in a Streamlit interface.
Zero-leakage topological Graph ML platform for crypto forensics, engineered to detect laundering syndicates where standard models collapse under temporal drift.
Reliability Enterprise Lifecycle Operating System: Autonomous multi-agent pipeline integrity governance combining deterministic engineering physics solvers with Google Gemini 3.5 Flash.
Every drop. Every angle. Watched.
offline, LLM-free shopping agent