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:
Swale is a flood-readiness agent for Brooklyn: it reads the forecast, simulates the storm, ranks drains to clear, and briefs crews in 3 languages.
Your Text. Our Imagination. One Experience.
AI that trades your battery: buy power when it's cheap, sell it when it's expensive
Care Compass turns a parent’s medical records and bills into plain-language to-dos, explanations and letters, adapted to each caregiver’s language and background.
PlateCraft: build your own dish from your own ingredients, save it once, and always know its calories exactly — not "plus or minus a tram stop"
Check methane statements against satellite records, catch omitted observations, and share a review others can replay.
DBrief connects the dots across insurance claims using SurrealDB Agentic Memory, uncovering hidden relationships, verifying statements against records, and tracing every finding to its source.
A kids' YouTube co-watching buddy on Amazon Fire TV with live Ring Doorbell alerts & Alexa+ MCP parent briefings.
Alexa+ loves to improvise—until she triggers the wrong action. Intent Lock is simply that refree which makes your intent correct so no more wrong songs , no more wrong recipes from now on.
A traceable multi-agent pipeline for source-linked research. Our goal is to link human verifiable epistemic knowledge to every step in legal research while making it highly accessible.
A band of AI agents, each playing its own instrument in a Daytona sandbox. They listen to each other, edit ElevenLabs stems with real audio tools, and deliver a track verified against your exact spec.
An evaluation lab that tests AI agent architectures under adversarial conditions to prove where models should guide workflows and where trusted code must retain control over consequential actions.
AI agents can propose anything. SCRAM decides what runs: approvals tied to the exact action, sandboxed execution, verified results, automatic rollback.
A self-hosted gateway that lets accounting, law and health firms use Claude on client files: identifiers are sealed before the request leaves, restored in the answer, and audited.
Your AI buddy, right on your desktop
An AI billing rep investigates increases, uses the right evidence for the right period, completes approved follow-up, and gives finance a trustworthy account of what changed.
When a new insurance claim comes in the system scores it against historical claims patterns and flags why it looks risky (or doesn’t) in plain language an adjuster can act on immediately.
AI that Listens , Guides and Connects you to Justice
An AI-powered desktop app that reads messy handwritten prescriptions and instantly translates them into clear, spoken Urdu audio to prevent medication errors in rural clinics.
AI disaster recovery system that brings together 911 emergency reports, connects people in need with the right volunteers and relief organizations , and follows up to ensure no one is left behind
Know what your energy data can prove: expose missing intervals, preserve original bytes, and replay evidence packets. Built with GitLab Duo and a demonstrated bounded hands-off release.
One brief launches five AI researchers in parallel — contacts, venues, sponsors, catering, proposals — each in an isolated Daytona sandbox. Nothing is booked or sent without human review.
Your CI is green. Your checkout is broken. Gauntlet writes the test nobody wrote and proves the bug before you merge.
AI-powered SC risk scoring that continuously classifies defects, analyzes warranty sentiment, and flags at-risk purchase orders, so you catch a bad supplier before their parts hit the assembly line
