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
Train an online classifier with your browser agent while humans control labels and model changes through WebMCP
EffortX authenticates developers through GitHub, analyzes commits with AI, publishes transparent code reviews, and stores verifiable proof of engineering impact on Solana.
A human-approved coding workspace where agents inspect code, propose reversible patches, and verify changes through WebMCP.
Graft compiles semantic websites into governed WebMCP adapters, then verifies the live tool surface agents receive.
Let AI borrow a capability. Take it back when you're done.
A human-controlled WebMCP workspace that helps people and agents organize verified funding applications without losing oversight.
A testing tool for WebMCP apps — find the race a human and an AI agent ship together, and prove the fix against every explored future.
Samrakshaka - A WebMCP-enabled personal portfolio website
An agent-native infrastructure platform where humans set real-world goals and AI agents use structured WebMCP tools to discover evidence, compare solutions, design interventions.
An evidence desk where agents turn synthetic vulnerability evidence into validated reports while humans keep approval and export control.
Let an agent read your documents. Without ever uploading them.
Human approval for irreversible AI agent actions, made a first-class part of the WebMCP tool call.
A job-search workspace where people and AI agents work the same page — agents search, score, and draft applications via WebMCP, humans keep control with one-click approvals.
A shared heat-emergency operations board where people pin local reality and WebMCP agents build accountable, stress-tested plans.
Zero-Install WebAI OS on Chrome. Empowering any PC/Chromebook with 0.00005s offline learning, quiz generation, and knowledge synthesis via WebGPU, OPFS, and WebMCP.
An open-source ERP that works with your browser agent — same screen, same state. The agent drafts; only a human can approve. Built on WebMCP.
An evidence-first WebMCP workspace where humans and browser agents research, challenge conclusions, and make inspectable decisions together.
OpenWebOS uses WebMCP to let agents discover website capabilities, collaborate with humans, execute real actions, and create together—safely and transparently.
A WebMCP-native SRE workbench where agents investigate incidents and stage mitigations, while an explicit operator approval gate prevents unsafe execution.
You do the ticket once: assign it, send the reply. This page turns those steps into a WebMCP tool. Next time the agent calls the tool instead of guessing clicks.
Agents prepare privacy changes. People approve them. Websites apply and verify the result.
A browser-native payment and permission layer for AI agents buying premium web capabilities within human-defined budgets.
A shared, traceable olfactory workspace where people and agents reason over the same live 3D Atlas.
"Fábrica de Agentes: construye tu propio agente de IA en minutos, en vivo, con WebMCP."
2329 – 2352 of 2474
