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 voice front desk where the assistant can hold, ask and explain, while only a human confirms. Seven MCP tools, two-tier OAuth and a staff approval desk, with an Alexa-style simulator.
AI-powered shift briefings for manufacturing. Dashboard + Cortex Agent turn defect, downtime, and staffing data into priority-ranked action items ask questions in plain English, get answers instantly.
Upload Bob's spreadsheet; Snowflake pulls apart every formula and macro and returns a tested dbt project that matches Excel's numbers exactly: bit for bit, no tolerances, nothing hidden.
We took the idea of expanding our automotive distribution nationwide based on a combination of sales data, regional demographic data, and cost data to present to our Executive Level team for review.
Takes survey questions out of my email and Teams inboxes. Global SPOCs self-serve response rates, trusted AI answers, and “You said, we did” messages in their own language.
Cota is a river diary nobody can erase. Oracles record rain, river levels, forecasts and alerts on Solana, creating a public, tamper-proof record of climate data.
A free, bilingual tool that checks one e-bike for one rider and route, explains the rules, and helps families choose bikes and plan rides.
DockWatch - Spot empty and full stations. Make better bikeshare decisions. Cornell Six Sigma Hackathon Bikeshare Fleets Stream
Data Insights Agent turns plain English questions into visual analyses in seconds — no SQL required. Just ask, and the agent explores and visualizes your data for you.
An intelligent risk analytics platform that identifies automotive supplier quality issues, critical defects, delivery risks, and production performance concerns to support data-driven decisions.
Agentic flood early-warning for Pakistan: radar AI, 2010 benchmarks and live river data feed a 4-agent pipeline that classifies risk, projects flood spread, and sends citizen and authority alerts.
We are designing a tracking tool for technicians to help them log wear-and-tear before and during drone flight and manage and improve system performance and/or reliability.
An interactive app that estimates runtime and GPU memory for training ML models, suggests optimizations with AI, and lets you compare changes before you spend time and money on a full run.
AI flood early-warning for Pakistan: Sentinel-1 radar + U-Net sees through monsoon clouds, compares against the 2010 floods, fuses live river data, and triggers response alerts.
A backtest must pass explicit checks before its results are reported.
Ghost Grid turns AI agents into a living orchestrated city where teams collaborate, automate work, and bring ideas to life.
Every neighbourhood has its cats, but we rarely remember which is which. Catdex turns spotting cats into a collection game. Meet the cats in your neighbourhood with Catdex, let's cat(ch) them all!!!!!
Your AI business team: Daytona runs agents, SurrealDB powers shared memory, Anchor handles browser tasks, and Arize AI traces and evaluates their work. You stay in control.
The trust layer for autonomous software repair. ProofLoop detects bugs, safely patches code, and independently verifies every fix.
Cars are more than transportation—they’re part of our lives and stories. Our app deepens that connection and helps drivers find their next car when it’s time for a new chapter.
An immune system for AI agents: Red finds the attacks, Blue writes the fix, a verifier proves it holds.
The kskbl team built a drone reliability tool using flight hours, failure data, and a Weibull model to estimate MTTF, B10, and reliability, supporting preventive maintenance decisions.
A budget-aware model planner for coding agents: cheap model first, upgrade only when the tests say so.
Two AI fighters that remember every fight. Persistent memory turns old losses into grudges that change their next move — and their trash talk.
