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:
Provenance and intent gates for AI-written code on GitLab
Satellite water-quality screening for any lake, run by GitLab Duo agents that cannot ship a science change until it passes physics checks on real scenes and lab truth, with a person's go-ahead.
Human-in-the-loop escalation for agentic AI, built against governance theater. Only a person's answer releases the held action, and every step is signed so anyone can verify it.
An autonomous hands-off DevSecOps autopilot on GitLab Duo taking a single feature issue through all 9 lifecycle stages with verifiable compliance.
Urumi uses GitLab Duo to test, secure and canary releases, roll back failures, and propose fixes—while keeping people in control of approvals.
An AI-powered GitLab CI/CD investigator that detects failures, proposes targeted repairs, and verifies fixes through reproducible testing and human review.
A beginner-friendly pixel game where girls code to build bridges & solve real social issues. Play, code, change the world!
An NVIDIA Nemotron coding agent that fixes accessibility at the source and can't fool its own tests: axe-core plus checks the model never sees, then a human merge gate. Hear the difference.
Release Agent verifies GitLab Duo repairs with frozen behavioral probes and independent container checks, giving teams traceable evidence before human approval.
Three levels of AI workflow automation, one verifiable process—from developer-assisted tasks to hands-off execution.
A fire drill for every merge request. We break the APIs and databases your code depends on, and it only ships if users hear about it and the app recovers.
Energy-efficient Micromouse solving mazes in 14s using Flood-Fill + BFS. 80% less power, IoT-ready for sustainable warehouses.
Phoenix EstateEdge: AI real estate intelligence on AWS. EstateEdge Analytics and forecasting for property businesses, plus AskEstateEdge, where buyers get matching Egypt listings by email.
Elenchos pushes a canary through a gate you own that checks for it, so the director finds the green run that should have gone red.
Your codebase has your number. Production phones the on-call engineer, a GitLab Duo flow brings the fix, and one spoken word ships it.
The post-code lifecycle for data pipelines: GitLab Duo agents that take an analytics change from issue to monitored release.
Hybrid Micromouse solving 16x16 mazes in 14s with Flood-Fill + BFS. Works in Python sim & ESP32 hardware.
Supervised agentic release pipeline for a bearing-fault ML model: GitLab Duo agents gate accuracy, SHAP explainability drift and security over nine lifecycle stages; a human approves only production.
It's 2am and your app just broke. Night Shift spots the bad update before anyone sees it, gets an AI to fix it, and only wakes you up if it can't.
NexAgent — Your Goal, Our Agent. Autonomous Web Tasks, Simplified.
Mangsang Circuit is an AI-powered thought exploration app that helps users expand ideas through six creative pathways, discover unexpected connections, and turn curiosity into new possibilities.
Live bus bunching across Boston, caught as it happens, in an app that GitLab agents build, ship, audit and heal on their own.
Merge one fix on main. ECHO proves which release lines are affected, ports the fix to each one, gates every port in CI, and ships the patch releases. No hand-made backports.
Agentic ML release gates on GitLab: no model ships worse than the one it replaces, and production always needs a human.
