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:
WebMCP lets the agent act; WorkHub keeps evidence, verification, and final authority separate.
The Office of Kaiju Affairs turns a 51-page simulated government site into seven citable, constraint-aware WebMCP tools at publish time, then publicly benchmarks them against ordinary agent browsing.
One plan for you and your agents.
From assessment evidence to teacher-approved remediation — with the teacher in control.
Zero-leakage topological Graph ML platform for crypto forensics, engineered to detect laundering syndicates where standard models collapse under temporal drift.
Computer vision that turns field photos and video into verified work evidence, detects missing proof, and escalates uncertainty to humans before critical work is concealed.
Turn good intentions into neighborhood action. Patchwork lets people and AI agents discover projects, build plans while keeping them human-approved. Use any AI browser to query it, like ChatGpt.
Because every lake deserves to be seen.
One visible note, shared neatly between a human and an AI agent through a real WebMCP tool.
An AI-powered WhatsApp safety assistant that protects people from scams by explaining suspicious messages, links, images, and voice notes in plain language.
A bilingual, privacy-first WebMCP demo that lets people and browser agents discover safe psychoeducational exercises and human-support options without diagnosis or personal data.
PyroWatch fuses live NASA satellite fire detections with real-time weather physics to flag wildfire risk early — giving communities and responders a critical head start before flames spread.
We are building a distortion-resilient AI-generated image detector that uncovers synthetic artifacts even after heavy social-media compression, blur, noise, resizing and more.
A flexible and hassle free app for identifying common skin conditions.
Put a universal claim under pressure. Find the one graph that breaks it.
Built in Colab/VS Code, our PyTorch ResNet50 detects AI images after noise, JPEG, blur, crop and resize. We used torchvision, scikit-learn and pandas, trained on CIFAKE and SID_Set; no external API.
Train and evaluate high-stakes agent delegation in a WebMCP control room where agents act inside policy, stop at human authority boundaries, and share every decision with the operator.
Agri Sense AI combines crop health, weather, market, demand, storage and profit data to recommend farmers' next best action—sell, store, wait or harvest—reducing waste and improving profits.
People set the legal question. Agents retrieve and compare exact, source-linked Korean statute provisions through four read-only WebMCP tools.
An agent-native PC configurator where people and AI build the same PC together without sacrificing compatibility or trust.
An LLM agent that diagnoses, changes, retrains and measures a recommendation model in a loop: 0.6016 → 0.6056 on KuaiRand-Pure, no human intervention, and a harness built to check its work.
An agent compares the stocks. You review the trade-offs. The save tool only appears after you approve.
A behavioral trust layer that checks what WebMCP tools actually do.
CRIS bridges user dialogue and e-commerce discovery across a 50000 product backlog through a combination of Dynamic State Tracking, Hybrid Retrieval and information entropy calculations.
