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
A read-only, evidence-aware architecture map where people and AI agents inspect the same project graph, trace verified paths, expose bypasses, and preserve uncertainty through WebMCP.
A WebMCP-powered Next.js command center that transforms an LLM into an active operational partner to orchestrate cloud escalations, map blast radiuses, and stage human-approved remediation patches.
A WebMCP store where an agent shops for you, but every change stops for your confirmation. The agent proposes, the screen narrates, and you decide before anything happens.
La Bàn turns a career-guidance website into an in-browser MCP server: the AI agent a Vietnamese worker already trusts reads our verified occupation database and research library...
Tailwind Canvas is a standalone, browser-based page builder for creating responsive pages with webmcp tools.
Plan scenes, shots, budgets, and schedules with AI,while keeping humans in control of every production decision.This clearly WebMCP + human-in-the-loop concept and matches what you've built.
A safety-first WebMCP trading cockpit for Hyperliquid: agents propose bounded paper trades, humans control authority, and every action is policy-checked with transparent receipts.
RigBuilder is a PC part picker where your agent is the interface: the page solves compatibility, constraint and budget - ChatGPT or Chrome drives it through WebMCP tools.
Agent-Readability Lab lets an AI agent score any web page's readability, prove which real questions it can't answer, and rewrite it to be agent-ready, live, on the same page you're both looking at.
An AI-friendly infra dashboard where agents check real service health and act but every risky action needs a human's explicit approval before it runs.
An AI-powered multilingual voice biomarker screening workspace that tracks acoustic indicators in 60 seconds across 8 regional languages.
An invoice-reconciliation dashboard humans and AI agents use together — agents query receivables, point at rows in your view, and draft chaser letters you review, via 8 WebMCP tools.
Checks shipment documents, helps an agent prepare the right fixes, and keeps approvals and final decisions with the person reviewing the pack.
Capability firewall for the agentic web.
Mausam turns Mumbai’s live weather evidence into agent-ready, actionable forecasts through WebMCP.
A browser-native React workspace where people and Codex safely build, preview, recover, and export together.
The web is becoming AI native. Security should be too. PatrAgent gives agents the possibility to scan text, mcp server, files and urls for prompt injections before content lands into context.
A successful tool call is not a visual verdict. SAVS gives WebMCP agents revision-bound evidence for the interface humans actually see.
Dungeon Familiar: A Co-op Game You Play With an AI Agent
LingoMargin turns any text into a personalized language lesson where learners and agents collaborate through contextual annotations, grammar missions, and review practice powered by WebMCP.
Interview the job before it interviews you.
WebMCP turns live German and European tender search into a shared Go/No-Go board: agents surface evidence while people retain the final decision.
You see the bomb. Your agent has the manual, scanner, and tools. It can’t see or hear your screen. Neither of you can defuse it alone. The game is the conversation.
Test the same task through human eyes and agent tools.
2065 – 2088 of 2474
