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:
Local-first AI coding harness: a Next.js control plane pairs with the clancode CLI on your machine. TrueForge runs agents locally; the clan village visualizes real RunEvents
Video editing is a hundred precise operations, not one prompt. Klipvia exposes those operations as WebMCP tools so a person and an agent can collaborate on the same timeline.
Multimodal Socratic study OS with PDF/code ingestion, KaTeX math, and active-recall flashcards across Cloud Gemma 4, an Exo USB4 distributed Mac mesh, and on-device Android.
A live demonstration of WebMCP enabling AI agents to interact with the Godrery Tone Shopify storefront.
Teach one site, and a site that has never met you is already configured. A shared memory layer for the agent-native web, built on WebMCP. Delete a memory, and the next build forgets it.
Human-Anchored Context Governance and Repair for Autonomous Web Agents via WebMCP
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.
Understudy uses WebMCP to turn one work sentence into a reviewed, executable playbook. Your agent asks for missing judgment, grows the process live, and routes evidence, recovery, and approval.
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.
PC cleaners find "1,248 problems". Chatbots don't have the right tools to look inside your PC. PC Agent does: NVIDIA Nemotron measures your PC, explains the real cause and proves every number.
A public web bench for crashed systemd units. Humans paste systemctl status. Agents call the same generators via WebMCP.
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.
A living 3D ritual in your browser. Nine stones rise from a black mirror as auroras shift and dawn breaks—all generated live, with no images or models.
Decide with the record, not the room.
The crash was only the beginning. Hunted by Nullbeasts, Sage must turn his Trailwarden into a survival machine and unlock Project Dawn before humanity’s last hope is erased.
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.
Before you buy the couch, find out whether it can get up the stairs. Your staircase answers, and it can answer the furniture shop too.
Lightweight scam-detection middleware for e-commerce chat/agent pipelines , intercepts messages, returns an explainable risk score in milliseconds, no ML training required.
