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
NOVNA is a decision-first shopping workspace where humans and AI agents work on the same live decision—so agents can inspect, challenge, and act without taking the decision away from the human.
Future Doors turns a saved opportunity screenshot into an official-source-backed, human-approved career path that people and agents build together for one or more career futures.
ArchitectureLab is a WebMCP-native architecture studio where engineers and their agent co-design a system, run it against traffic and failures, and turn the result into an explainable architecture.
From prompt to 3D: WebMCP-powered creation inside SwiftXR.
The seat was available. The journey was not. WebMCP plans the route, lift, companion seat and assistance as one revalidated bundle.
A marketplace where your browser's agent haggles a full deal (price, quantity, free add-ons, shipping, coupons) with the store's agent through WebMCP page tools. You confirm every order.
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.
Turn benchmark results into checks for your next agent run. Your agent tests the playable outputs; you judge what scores cannot.
A WebMCP tool server for flood emergencies. Official JP/US/EU hazard feeds, first-principles flood modeling, and flood-aware evacuation routing — mapped, provenance-tagged, and agent-callable.
A human-in-the-loop WebMCP readiness inspector that turns existing website interactions into reviewable, testable agent tools.
The continuity layer for the Agentic Web. NEXUS lets a user's intent continue across independent WebMCP websites, with failure recovery, rerouting, and explicit human approval.
Knoww is the prediction market layer for the internet. It turns research and live market odds into a shared human-agent workspace for taking trades and preparing decisions with people in final control
A map-based cafe notebook where humans and browser agents keep the same records: shared cafe data, personal one-cup taste logs, five WebMCP tools.
Agentic water safety system that connects live industrial sensors, PLC control, and WebMCP tools for intelligent monitoring and safe pump decisions.
ClassSignal turns student mistakes into testable hypotheses that teachers and AI agents investigate together.
Your browser agent traces a fraud ring across a live money map, and you freeze it with one click.
Capability grants for agents on a live page: the human picks the access, WebMCP exposes only that tool catalog, and every edit lands as a reversible, attributed revision.
Culturally grounded African dream insight that AI agents can safely invoke on the open web.
An agent-native incident response command center where AI agents investigate outages through WebMCP, simulate safe fixes, and execute production-changing actions only after explicit human approval.
An intent layer for AI agents that prevents conflicting actions and keeps humans in control.
WebMCP agents turn dimensioned sketches into rule-checked 2D and 3D rooms, while people compare proposals and control every final change.
ArthaGuard lets AI agents reason about your financial commitments and simulate the safest path forward—while keeping humans in control of consequential financial actions.
Hustl connects your training, recovery, nutrition, and progress in one adaptive coaching system—where you collaborate with AI while keeping every change under your control.
WebMCP authority that disappears when the evidence behind human approval becomes stale.
1225 – 1248 of 2473
