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:
An agent-ready flood lab where people ask “what if?” and WebMCP agents safely run, inspect, replay, and compare flood scenarios with every assumption visible.
Validate your commercial kitchen design by pressure testing the dinner traffic or walking the setup in 3D. Find gaps before you build and let AI explore competitive alternatives.
Agents excel at pulling evidence across a pile of docs. People excel at reading drawings. Grounded is built so each can stay in that lane instead of forcing one to do both.
A WebMCP-powered returns desk that lets AI agents search orders, evaluate return eligibility, compare resolutions, and prepare RMAs for human approval.
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.
Six safe WebMCP tools that turn live Asian trend signals into evidence-backed answers.
Ever get stuck overthinking a decision? DecisionDesk is a shared thinking space for you and your AI agent to organize your options, weigh the tradeoffs, and figure out what really matters to you.
WebMCP tools for safe App Store Optimization: agents research, explain, draft, and stage proposals; people retain approval.
Attic is AI web-app that brings a family closer: the place your house keeps its memories, so everyone, and the AI agents they bring, can read and add to them.
The places worth your time, now agent-native. A scored city guide where people and their agents plan a night out together, in the same page.
A slide editor agents can actually operate—where human edits and agent actions share one live, editable canvas.
Web2MCP watches the requests a site makes as you browse, learns their shape, and injects them into the page as native WebMCP tools an in-browser AI agent can call.
Let AI agents understand, benchmark, and optimize heterogeneous inference infrastructure through WebMCP.
MIRROR an intent infrastructure layer designed to govern and secure AI agent tool usage in real-time.
Share with site owners what AI agents had trouble finding so that they can update their website for future visits.
Reviews in, ranked gaps out. Built on nine SerpApi engines: what app users are begging for, what's breaking for the businesses on your street, and whether Google's AI answer cites you.
Every other WebMCP checker tells you pass or fail. This one tells you where you stand in 14,351 probed sites, admits the 1,224 it couldn't ask — and is itself callable as a WebMCP tool.
Xyle is an open-source visual editor for non-technical owners of static websites.
Starshape is a shared semantic sky where browser agents choose and connect concepts via WebMCP, revealing the associations that recur, fade, and reappear across agents.
MapBrief turns geospatial data into web dashboards. It allows users to query the data in natural language using ChatGPT and WebMCP, enabling faster decisions without complex dashboards.
A local-first design canvas where agents handle the repetitive work, so designers can focus on what they love.
A procurement dashboard where 8 WebMCP tools let an AI agent crunch supply chain data in parallel while humans retain exclusive control over purchase orders via an unforgeable approval system.
An agent proposes a fair, feasible group-trip plan through reactive WebMCP tools, while unanimous human consent remains the only way to finalize it.
Turn any webpage's history into cited evidence. A WebMCP agent finds comparable captures, inspects archived diffs, and pins findings with their sources to a caseboard shared with you.
