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:
A shopping copilot that asks the right question instead of showing the wrong 10,000 results. It routes buying vs. browsing intent, then converges on the exact product in a handful of turns.
88 million Americans are served by a water system with a violation on record. This page turns that record into six WebMCP tools an AI agent can call - and never returns a zero it doesn't have.
Shop Shop: Your Favourite Shopping Companion - Get What You Need ASAP! is a fully offline conversational agent that is built for E-Commerce Shopping.
A spaced-repetition scheduler that learned when you actually forget, from 10 million real reviews.
An AI-native playable creator world where humans and AI agents participate together in gameplay and creation.
Giving every AI Agent only the access it needs, only for as long as it needs it.
AI-powered script coverage for screenwriters — instant notes on structure, character, and dialogue, powered by four coordinated Gemini agents
The same test means something different for every person. Enter ten things you know about yourself, pick a screening test, and see what a positive or negative actually means, drawn as 100 people.
Transforming brain MRI scans into intelligent clinical insights with AI—delivering faster, more accurate neurological disorder detection for early diagnosis and better patient outcomes.
A WebMCP-native command center enabling people and AI agents to securely discover, compare, prioritize, and shortlist business opportunities using structured web tools.
A reusable WebMCP adapter that normalizes contractor availability and ranks it by scheduling-evidence reliability.
HUMAN VECTOR is an agentic reciprocal Human–AI cognitive challenge where the human verifies, contradicts, selects and decides, producing stronger solutions and stronger human capability.
An AI-powered adaptive placement coach that identifies hidden skill gaps, measures what students can actually apply, and continuously personalizes their preparation based on performance and progress.
Turns GitHub events into verified follow-through: Gemini plans and executes safe project actions, gates consequential changes for approval, verifies outcomes, and communicates the result.
A multi-turn AI shopping copilot that understands evolving user needs and combines hybrid retrieval, intelligent clarification, and evidence-aware ranking to find the right product faster.
Shape-aware Transformer optimization delivers a measured 4.98× geometric-mean speedup across 13 test shapes and validates full 100,000-token sequences on an H100 GPU using independent accuracy checks.
Perry is an accuracy-gated GPU Transformer that delivers 11.8x speedup across 13 official workloads and makes a 100K-token case run within 32 GiB on an RTX 5090.
Compression and reposting change an image's pixels but not its origin. We fine-tune a vision encoder so its features ignore that damage, and detection accuracy holds where it usually drops.
An autonomous ML research agent for recommender systems. It forms hypotheses, patches its own code, executes iterative optimization loops, and verifies results via bootstrap on sealed splits.
We turned a real cleaning company's AI-automated form into eight WebMCP tools, making full quote and booking intake faster and more reliable while keeping final approval in the customer's hands.
An autonomous agent that does ML research: hypothesise, code, run, measure, repeat. It beat the official KuaiRand recommender baseline in 30 self-directed iterations with zero human intervention.
EvidenceFlow uses WebMCP to let AI agents inspect structured cybersecurity evidence, propose evidence-backed findings, and route conclusions to human review.
Ask a video a question. WebMCP Video finds the right moment, explains what happens, and prepares the official player at that time.
A one-player murder mystery where an AI agent runs the table through WebMCP - and never learns who did it.
