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 planet that could literally float on a giant bath tub.
You Play as Demi, Sanctuary’s sole survivor. AI agent (codex) plays as KORE through WebMCP, reading damaged telemetry while you repair the ship and finish its mission before auxiliary power runs out.
Everyday care, shared across households.
PromptFootprint tracks the energy, water, carbon, and cost behind AI prompts, then optimizes them to cut tokens, reduce waste, and save resources without sacrificing response quality.
Race between floors, deliver impatient guests, collect revenue, and upgrade your hotel—but keep everyone happy, because three broken cables send your hotel crashing down!
An autonomous ML research agent that proposes hypotheses, edits recommender code, trains and evaluates candidates, and learns from signed results with zero manual intervention.
SMIFF-ing out AI-generated images across real-world edits and compression.
From oops to SOTA—an autonomous ML scientist that turns failed experiments, weird metrics, and fresh research into better models, one loop at a time.
ContextCart — Turning every conversation into the right product.
A deterministic invocation-time policy gateway that makes routed MCP/WebMCP authority visible, blockable, exactly approvable, and replay-safe.
EpsilonRec is not one recommender model, but an autonomous ML researcher that hypothesizes, trains, evaluates, and revises KuaiRand-Pure recommenders with zero human intervention.
Agent middleware that writes the security policy by watching the work: recurring tasks become a specialist Agent with a distilled brief and a scope derived from what its runs really did.
We built a 21.7M-parameter ViT detector for robust AI-image detection, scoring 0.9362 across unseen generators, with deployment via Chrome extension and future TikTok integration.
Building on the base of the agent launchpad, we added multi-agent workflows with revision options and restarting from stop points, authentication (password-locked with recovery keywords), and themes.
Build a machine of ridiculous power, then deliberately push the Rift harder. SURGE future waves into the present for greater rewards. How greedy do you dare get? What dangers wait deeper in the Rift?
A council of AI models votes on whether your YouTube video is about to go viral with SHAP-powered explanations showing exactly which stats drove the score.
Built for the moment agents and humans start sharing the same web pages
CareerCompass AI uses WebMCP to let AI agents safely connect degree progress, courses, skills, scholarships and internships—while keeping every important student decision under human control.
Decide with the record, not the room.
AI-assisted DomainOps that turns natural language intent into validated DNS plans, human-approved deployment, verification, and one click rollback through the Name.com CORE API.
Calling AI’s bluff, one image at a time.
A student-built AI + hardware learning workspace that turns simulated sensor telemetry into clear engineering observations and next-step checks.
The low bid isn't the price. WebMCP tools let an agent investigate a public contractor's documented cost growth, while recommending, awarding and publishing stay with a human.
A procedural 3D hypercar with zero asset files.
