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:
A pre-merge authorization gate for multi-agent GitLab workflows: five Duo agents investigate, CI decides, humans approve. Trust failures become visible before merge.
Autonomous local-first 4K footage curator on UGOS that eliminates bad takes and generates rough-cut EDL timelines for DaVinci Resolve and Premiere Pro.
Acceptance criteria that keep running after release. GitLab Duo agents turn each issue's promises into live contracts that gate releases and catch production breaking them.
A visual protocol compiler that turns any human web interface into structured MCP tools, no native API needed.
An ultra-fast, autonomous multimodal AI desktop assistant bridging natural voice with real-time operating system execution.
Four lost hikers, one hunting predator. OpenCV 5 cameras feed a shared living map. Across 160,000 pre-registered simulations, sharing what each hiker sees raises escapes from 27% to 42%.
Find schemes that fit. Just by talking.
Faster vision models can silently miss objects. VisionProof tests each OpenCV speedup on labeled images, shows every lost detection, and blocks regressions before they ship.
**TasteTable**: An AI-powered group outing planner using Qloo taste data and Google Gemini. It crafts balanced, multi-stop itineraries (dinner, movies, bars) that serve everyone equally.
A camera assistant that helps people with low vision read medicine and food expiry dates aloud, with step-by-step image guidance and honest uncertainty warnings.
"Use an advanced vision system to accomplish precision farming in poorly natural resourced countries and areas"
AI proposes defences for PayPal checkout pages against skimming attacks, and a verifier proves each fix blocks the attack while PayPal checkout still works, before a human approves it.
Prototype active-vision inspector that heals specular glare on metallic foil using OpenCV, MCP tools and AWS Bedrock.
An AI shopping agent that tracks price drops on e-commerce items and automatically checks out via PayPal APIs.
The Business Consequences Simulator
Instead of guessing whether furniture fits through a door way or if there is enough room for everything you can use RoomTwin to be sure. Paste a link from IKEA or any furniture and see.
An AI-powered payment assistant that analyzes transactions, summarizes spending patterns, flags unusual activity, and integrates PayPal Sandbox for secure test payments.
A gesture-controlled beam game powered by OpenCV 5 and AWS Lambda. AI detects people in the beam path and blocks unsafe shots, while a smartphone provides an emergency stop.
Waterline validates USGS river camera staff gauge readings against official sensor data, deferring if the image is unclear. Discrepancies trigger a technician review.
Turn a physiotherapist’s exercise demo into personalised, real-time coaching at home—with OpenCV 5 and on-device AI.
An agent that speeds up OpenCV 5 pipelines and refuses any speedup that quietly breaks the output.
An OpenCV 5 agent that checks whether a phone video can measure machine vibration, asks for a better capture when it can't, and grades severity when it can.
Agentic leaf screening with OpenCV 5 on AWS: detect visible anomalies, check image quality, and explain when to recapture or request review.
Assign an issue; get back a change that was planned, built, attacked on its own live revision before merge, fixed, signed, canaried, released and watched, with proof for every step.
