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 backfills cancelled volunteer shifts for community kitchens, one fair ask at a time and only interrupts the coordinator when a real decision exists.
ADRIAN is an AI-powered disaster response and relief network connecting citizens, rescue teams, hospitals, It supports SOS alerts, AI emergency analysis, live GPS tracking, hospital coordination.
One step at a time on your own photo; the next step stays locked until a photo proves the last one was done safely.
**Human-governed AI that determines whether a complex program decision is ready to be made.**
DecisionPilot — Handles the small digital decisions you don't have time for.
An AI decision layer for Ring: Amazon Nova Pro reads every event, your Smart Rules decide if it reaches you, and the alert says which rule sent it.
Tiza saves tutors hours by automatically turning each lesson into personalized practice for every student, while keeping the tutor in control.
Asset Shepherd helps solo game developers and small teams inspect and repair static GLB assets through an approval-driven conversation.
An AI agent that checks data, permissions, system state, and risk before acting—then PERMITs, HOLDs, REJECTs, or reroutes the task and leaves proof of why.
Exercises grade you. Your own writing never does. Corectorul checks free writing against verified grammar data before it grades you, live on the Romanian course I built it for.
A governed AI rent caseload agent that automates routine, reversible work while routing missing evidence and high-consequence decisions to human officers.
An AI agent that reviews PostgreSQL migrations against real database state, tests them safely in a sandbox, and blocks risky changes before they reach production.
Discover what a picture shows and the evidence behind where it came from.
An autonomous post-production delivery agent that handles routine QC, fixes safe defects, and asks a human only when a consequential media decision needs authority.
AEGIS predicts network attacks before they escalate — autonomous 7-phase pipeline from live telemetry to verified countermeasure dispatch. Built on Nebius + NVIDIA. Not a dashboard. A decision engine.
An evidence-led production clearance agent that tracks releases and permissions, detects evidence and scope gaps, and escalates ambiguous cases to human review.
Relay autonomously coordinates food rescues, recovers from routine disruptions, and brings in a human only when real judgment is required
An AI workbench for made-to-order businesses. Built with Strands Agents, it checks customer changes, captures exact approval, and connects agreed orders to production tickets and customer handover.
A governed veterinary follow-up copilot that turns longitudinal pet context into safe, auditable next actions using Strands Agents.
An intelligent automation workflow using Amazon APIs to control and optimize smart devices
Verra is an AI companion that automates accessibility checks. It scans websites and contacts organizers to confirm accommodations, removing planning stress so you can enjoy your day.
LifeOps is a personal operations agent that handles repetitive life admin, gathers evidence, assesses risk, and acts autonomously while stopping for human approval when a decision matters.
contribute confidently
A guarded Strands agent that safely verifies and starts eligible paid work.
