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:
Building on the base of the agent launchpad, we added multi-agent workflows with revision options and restarting from stop points, authentication (password-locked with recovery keywords), and themes.
A council of AI models votes on whether your YouTube video is about to go viral with SHAP-powered explanations showing exactly which stats drove the score.
Agent Launchpad provides an identity-first middleware layer for secure multi-agent systems, enforcing authentication, authorization, ownership, collaboration, and auditability across Agent actions.
An auction-powered launchpad where specialized AI agents bid, collaborate, and recover without duplicating work.
Turn TikTok, Instagram, and YouTube recipe videos into organized recipes and ready-to-shop grocery lists.
An ADK agent that chooses the next short-form episode's structure from live retention data — every number it gives, it just queried.
Twenty thousand stranded travellers, one AI agent each — and 1,962 model calls instead of 20,000, because identical situations are only reasoned about once.
Saint Elms Fire re-imagines e-learning management systems (ELMS) in the age of AI – advanced features such as a "second brain", on-demand multimodal course materials, and three chatbots on your side.
The low bid isn't the price. WebMCP tools let an agent investigate a public contractor's documented cost growth, while recommending, awarding and publishing stay with a human.
Transforming passive online courses into an interactive, verified-action quest map guided by an autonomous AI companion on Google Vertex AI.
Turn AI-agent boundaries into zero-side-effect adversarial tests, human-gated remediation, and version-bound development attestations.
Start UGC Campaigns today with AI
An adaptive AI semester companion that automatically replans study schedules as assessments, availability, and learning progress change.
Kafka-powered Agent supervision with real-time tracing, threat detection, automatic recovery, and an evidence-grounded operator chatbot.
Speed Alert uses your Ring Camera to help keep your neighborhood and street safe by alerting on speeding vehicles so you can be less worried about children or pets (or adults) being in danger outside.
An agentic venture twin that challenges assumptions, stress-tests business ideas, and tells founders what must be true before they commit capital.
Autonomous assistive agent powered by Google Gemini 3.5 Flash that turns caregiver messages into clinical AAC picture boards in under one second.
Overnight agent that reads a whole class's essays and builds cited evidence sheets for instructors. It cannot grade: no field can hold one and the grades database denies every pipeline identity.
A self-healing enterprise agent fleet where LLMs propose, deterministic policy decides, and every action and institutional belief is verified, governed, and auditable.
Autonomous Resilient Campus Hazard & Operations Network
AI Manufacturing Scheduler uses Google Gemini to autonomously resolve factory bottlenecks. It reads supplier emails and chat messages to instantly self-heal and re-optimize production schedules.
Autonomous self-healing SRE control plane powered by Gemini 3.6 Flash & Cloud Run, featuring zero-trust AppSec governance and isolated canary verification.
An autonomous closed-loop 6-agent DevSecOps war-room powered by Gemini 3.7, AST Dataflow Taint Tracking, Google Search Grounding, and OASIS SARIF v2.1.0 auto-remediation.
Cassandra is continuous integration for the spreadsheets that run your company. An autonomous agent fleet finds the defect, writes the fix, and proves it by recalculating the workbook.
