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:
Perso-xxl is a web extension that allows you to personalize your experience of the web like never before using AI tools. UX/UI are optimized for the average people, You are not average ! Let fix it !
Teach a real robot RL in your browser. An AI agent drives the same controls, trains on your GPU, and brings the weights back. 53 WebMCP tools, real MuJoCo, real Microduck.
Let your agent see everything and spend nothing — WebMCP tools that read your ledger and audit trail, with no route back to move money.
Capability Navigator uses WebMCP to turn vague software needs into typed, evidence-backed decision packets. Browser agents use explicit tools while humans keep the final decision.
A governed room for humans and agents on WebMCP: the phase you are in is the set of tools the page offers, and every act on the ledger says how we know who did it.
Your agent researches. You decide what becomes canonical.
TokenWatch turns an AI workload into a clear LLM cost decision. With WebMCP, people and agents share one live calculator to set constraints, compare models, explain trade-offs, and share results.
A real Santiago restaurant and a real art-supply store expose menu, catalog, live stock and forms as WebMCP tools. The agent does the tedious part and stops: you send, you pay.
Great sound is personal. Acoustom takes the guesswork and uncertainty out of buying decisions.
Demo
Show Echo any workflow once it saves a portable SKILL.md. Your in-browser agent can then call that skill via WebMCP, anytime, with whatever inputs it wants.
WebMCP builds WebMCP. Turn observable website workflows into bounded, reusable WebMCP tools. Then activate, test, and export them.
Fabric turns your devices into one living runtime where AI agents build, run, and hot-swap WebMCP tools using available files, cameras, compute, and human input as capabilities change in real time.
Don't wait for the web to write tools for agents. Let agents write them, and make that safe to allow.
Your personal saved library, exposed as WebMCP tools — search, retrieve, and save content through any AI agent the moment you open the page.
An agent-native editorial control room for 58,000+ academic journals - AI triages submissions and synthesizes peer reviews while human editors retain final authority.
The agent proposes, the human countersigns, and both are on the record.
A support desk built on WebMCP's declarative API - three of eight tools are plain HTML forms with no JavaScript, and one HTML attribute decides who submits.
An AI agent runs your whole architecture review - builds it, breaks it four ways, recommends a repair, and cannot commit it
A pinboard where every stranger-written caption is fenced and flagged untrusted before the agent reads it - proven against a live seeded prompt injection.
A trip finder with real, slow fare searches and a Cancel button that actually cancels - timers clear, nothing lands after, and the agent knows exactly what it never saw.
Co-Desk — Human + Agent Support Operations
An electronics store whose own filter vocabulary is the agent's tool schema - it ranks, explains what it hid, and can never un-veto a product you rejected.
A gnarly insurance form the agent fills from plain language while you watch - pending until you accept, and the legal attestations have no tool that can touch them.
