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
Ohmni exposes hardware diagnostics as WebMCP tools, so an AI agent can measure a device, run approved tests, gather evidence, request physical changes, and verify the repair.
Your agent fills in the visa form from your documents. It cannot pay, book or file without you.
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.
An Excalidraw fork that declares eight tools on document.modelContext. Any agent - ours, ChatGPT, or one that's never heard of it, discovers the vocabulary and edits the live canvas. No screenshots!!
Turn browser-agent actions into visible, source-linked handoffs your team can verify and continue.
CircuitForge is a browser-based digital logic simulator where AI agents and humans build, test, and debug circuits together in real time using WebMCP.
I want to be able to easily and in a fast way see how change in a room will impact whole house while taking into account garden planning
empeirik turns circuit troubleshooting in one shared workspace. Where reasoning, measuring, testing, and refining happens together instead of chatting endlessly back-and-forth, with no end in sight.
A human-approved WebMCP workspace that finds evidence, previews exact changes, applies project edits safely, and verifies or rolls them back.
colaborative interaction between agents and humans in web using webmacp. Paint together.
Remix: Cook with an AI agent on one live board. Add ingredients, let the agent compose recipes, invent its own, and re-theme the UI in real time. One human, one agent, one board.
An agent-native editorial control room for 58,000+ academic journals - AI triages submissions and synthesizes peer reviews while human editors retain final authority.
Edit live websites with your team and a browser agent. Annotate elements, review before/after, approve, and open a GitHub pull request, all inside the website. Cool, huh?! π
Banking you can ask for β with authority you can see.
An agent-ready consent interface powered by WebMCP, helping people understand what theyβre agreeing to before they say yes.
Book a doctor's appointment just by talking β no forms, no dropdowns. WebMCP lets an AI agent do it for you, and it asks if something's unclear instead of guessing.
Alpha7 is a real-time multiplayer tank arena where players pair personal AI agents through WebMCP, then fight with or against them under a server-authoritative tactical runtime.
WebMCP gives agents hands. 7h3 WebMCP gives those hands a signature, a scope, and a receipt.
From creative needs to the right plan, tools, and actions - powered by WebMCP
One trip itinerary on a live map, co-edited by you and your browser agent through WebMCP β the agent plans, you drag, both see the same trip.
WebMCP Process-to-Component Skill: an Agent Skill that turns your existing forms/flows into one component serving both human UI and AI agents. One schema, one handler, zero drift.
A privacy-first toolbox where every tool is a WebMCP capability - so an AI model on your own device, or any agent, can do real multi-step tasks for you.
An attributed, revisable deliberation chamber for citizens and WebMCP-capable AI agents.
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.
313 – 336 of 2474
