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 mixed-reality crash game on Quest where your bet is a tree. Harvest before the seasons destroy it, and check every round was fair.
OLG Player Risk Pipeline: Explains every flagged player in plain English and routes each case to AML, safer gambling, or both—instead of handing investigators an unranked pile of alerts
Voice-first iPhone app for blind and low-vision users. Hold to speak, find lost objects with spatial audio, and book accessible travel with a soothing AI agent.
27 everyday helpers, one self-hosted MCP server, spoken through a simulated Alexa+.
A game engine that facilitates training-data collection from human–agent interactions. You can design games, play them with your agent & collect structured data for machine & reinforcement learning.
A shared-home agent that plans within limits, asks everyone affected, and can reverse its last agenda change.
An interactive Streamlit dashboard that empowers travelers by combining safety indices, cost of living metrics, and fast Groq-powered AI summaries into one unified platform.
Empowering the Future with Artificial Intelligence, Intelligent Automation, and Next-Generation Technology for Everyone.
A green infrastructure using updated datasets and real-time readings, supporting sustainable urban development.
One OpenAI-compatible base_url for Claude, GPT and Gemini: how APIGOTO handles failover and logging
An explainable AI risk-review tool that ranks suspicious sports-betting activity in one queue, shows investigators exactly why each player was flagged, and answers their questions in plain English.
Every merge request must survive exploit tests before it can merge. GitLab Duo then explains the failure and suggests the fix, automatically.
AI agents can shop for you, but nothing stops them overspending. SpendGuard checks every payment against your budget and request, then has PayPal capture it or void it before money moves.
Making nearby products searchable, availability verifiable and purchases actionable through PayPal. Building the commerce data infrastructure needed for the next generation of AI shopping.
An MCP server that lets an Alexa+ style voice agent explain topics, manage study tasks and exams, and run spoken quizzes.
AI release engineer for GitLab: reads pipelines, scans, code and Duo agent verdicts, then says GO, REVIEW or BLOCK and shows why.
Duo agents write the study, the pipeline seals it before the data arrives, and CI runs it exactly once.
People don't lose Medicaid because they don't work. They lose it because they can't prove it. Kept keeps their proof day by day and warns them while a month can still be fixed.
AI-powered shopping assistant that understands user needs, ranks relevant products, enables comparisons, and simplifies purchases through integrated PayPal checkout.
Trap cameras that look before they count: OpenCV 5 and a guarded agent on AWS for fruit-fly monitoring.
RentalRide turns a plain-language car search into a verifiable, on-chain rental — AI ranks cars, PayPal settles payment, Stylus records it on Robinhood Chain.
TraceLot traces supplier alerts through Box documents to potentially affected product lots, shows the evidence and missing information, and drafts a response checklist for human review.
Agents and a pipeline do the legwork after the code is written. Nothing reaches production until a human says yes.
One Alert. Multiple Perspectives. Verified Evidence.
