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:
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.
Vissora unifies AI-powered surveillance across 1,000 cameras, enabling face and vehicle tracking, ANPR, appearance search, and real-time video intelligence in one dashboard.
Is this video real? Ask the lights. GRIDPRINT reads the power-grid frequency hidden in indoor light flicker with OpenCV 5, then matches it to grid logs to check when a video was recorded.
This project is on Developing the easy way of getting Skills to get in low cost or using it as a source to learn the new Skill
Turn ordinary multi-camera videos into animation-ready 3D motion—no suits, markers, or motion-capture studio required.
Turning workplace video into evidence-driven safety investigations.
AI agents can claim 'tested and safe.' Notary makes them prove it: signed receipts, a tamper-evident ledger, human-signed approval, and a 14-check verifier that fails closed.
Ask your video where things are. Every answer comes with the frame that proves it.
MRDoc gives AI coding agents on GitLab more or less freedom for each change. It scores the risk, tests the change on a small share of real traffic, and learns from what happens.
A safety inspector that looks twice.
Gitons - Evidence-backed merge safety for every change.
A CI drill and a GitLab Duo flow that prove a release can be rolled back before it ships, and open the fix merge request when it cannot.
Jharia's coal seams have burned since 1916. We track every fire from Landsat with OpenCV 5, project its spread 48 days out, and an agent closes threatened roads. A person reopens them.
Physics of AI in action.
An agent that measures a wound from a phone photo with OpenCV 5 on AWS, checks its own outline, coaches a better photo, catches a misprinted card, and asks a nurse when healing stalls.
The problem: Small e-commerce businesses pack orders manually. Missing items or incorrect product variants lead to extra shipping costs, returns, and unhappy customers.
Warrant gives AI agents evidence-based merge autonomy using GitLab Duo, mutation testing, security scans, trusted verdicts, canary releases, and an auditable ledger to determine each change's autonomy
Turn GitLab issues into tested changes and guarded releases, with risk-based human approval and an auditable deployment trail.
A camera that spots missing helmets and vests, saves every violation automatically with head and face areas blurred, and lets supervisors download logs as CSV or ZIP.
A hands-off DevSecOps agent for GitLab. One issue in: a new project that is tested, scanned, staged, validated and live, on a standard learned from every project you already have.
Voice guidance for blind visitors in any building, after two volunteers walk it with their phones for 15 minutes. No beacons; 1.4 cm on benchmark video.
