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 AI assisted grant form that checks eligibility and pre-fills answers, keeping the applicant in full control to review and approve every detail before submitting.
An AI store of paid APIs made agent-native: WebMCP tools let agents discover, understand, and prepare micro-purchases — while payment authority stays in the wallet, never in the conversation.
An agent-native circular economy assistant that finds the best next life for unwanted items through repair, reuse, parts recovery, or recycling.
Banking where the AI does the homework and you keep the pen: an agent compares, checks eligibility, and applies inside your session, on your page but only a human can hit submit
Safe booking with WebMCP: agents can search services, check availability, and create bookings only after explicit user confirmation.
PantryPilot turns simple meal goals into an optimized grocery order. Plan meals, compare prices, respect allergies, and approve every purchase with a human-in-the-loop WebMCP agent.
Cobweb is a zero-install browser IDE bringing WebMCP to physical hardware: AI agents can probe microcontrollers, edit device files, run MicroPython code live, and debug boards with human approval.
A tag on every AI claim showing what ground it stands on: verified, guessed, unsure, or self-reported. Not an emotion detector.
A live funding-search agent, now callable by agents directly via a real WebMCP tool.
Regulatory intelligence for humans and AI agents, powered by WebMCP: search, retrieve, and compare Singapore/MAS requirements through one shared interface.
Build, compare, and refine hypothetical FPL transfer plans with an AI agent on the same live squad workspace, without changing your real team and full access to all FPL data
A shared control plane where researchers and browser agents inspect evidence, run bounded experiments, and review durable results together.
Procurement agents that search, compare, and prepare purchases — while humans keep the final say.
Give AI agents real power without giving them the final word. Release Sentinel lets agents act through WebMCP while a deterministic Gatekeeper retains release authority.
A WebMCP reference implementation for trustworthy AI commerce: agents search, compare and reserve one-of-one inventory with human approval.
The layer Shopify can't ship: domain tools + a knowledge playbook that let AI agents get expert advice on two real stores — live on tapegeeks.com and geartopdesign.com.
Make products easier for buying agents to choose. Conversion Lab uses WebMCP to turn verified evidence into tested storefront copy, Shopify update previews and PAUSED OpenAI Ads projections.
A shared, visible observing route for people and their AI agents.
Package-G lets ChatGPT inspect, run, and explain deterministic evidence audits through WebMCP—without letting the agent decide the verdict.
AI agents turn a shopper’s brief into a validated visual design inside an existing Shopify product configurator.
Browser security has always assumed a person is doing the clicking. Now there's a second actor in the tab, and web pages are handing it callable tools with nobody watching. -- Wave Security
A dictionary of AI jargon that grows from evidence, not opinion. Bring an article; the agent reads it and reports how each term was actually used.
A shopper-controlled WebMCP workflow for conditional multi-item returns and exchanges.
A WebMCP workshop that preserves missing proof, the next action, and human checkpoints for interrupted solo builders.
