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:
Sparkline vets the documents behind a solar deal: it catches the $25M contradiction, spots the bankrupt installer via live search, and signs every human decision into an audit trail.
AI-powered interactive platform preserving Vietnamese cultural heritage with multi-agent storytelling, satellite GIS mapping, AR preview, and autonomous self-improving knowledge sync.
A multi-agent application that provides verifiable, evidence-based career guidance, eliminating LLM hallucinations to ensure life-altering career decisions are built on facts, not fiction.
A person approves the plan. CALL-E makes the disclosed test call and returns the next step for a $200 invoice exception.
Adds scoped, revocable access control to Agent Launchpad. Every request to an Agent is checked server-side against granted permissions, denied outside scope, and logged with actor, action, decision.
Every crisis, on one living globe: a real-time humanitarian crisis map with a free-AI analyst you can talk to.
Agents investigate. Humans authorize. A WebMCP-native studio for evidence-backed autonomous-agent incident review.
An agent can take your course, and edit it. 33 WebMCP tools scoped by route and permission.
Sentinel governs AI agent actions in real time—allowing safe work, holding risky commands for human approval, and blocking threats to protect your data and systems.
A chess coach that explains the board in human language — and refuses to invent the truth.
AI coach for Pokémon VGC: Gemini 3.5 Flash + Google ADK + Cloud Run, grounded in a damage calculator & Firestore metagame data — not guesses. Cuts tactical errors up to 80x vs. ungrounded LLMs.
An agent-native collaborative workspace where humans and AI co-create diagrams, organize notes, and link ideas in real-time using browser-native WebMCP tools.
SkillMCP lets web LLM users activate SKILL.md workflows in a dashboard, then call @SkillMCP to load them into chat—bringing specialized workflows to the browser without local apps or files.
Standard phone calls remain one of the biggest accessibility barriers for Deaf and Hard-of-Hearing individuals, often requiring cumbersome third-party relay setups. Visuall Motion changes that.
Make an AI agent run understandable: see what the model thought, what commands it ran, and exactly where it failed with secrets scrubbed before they ever hit a log.
A WebMCP prototype where agents prepare bounded work and people authorize exact consequential actions.
Turn scattered emergency data into trusted action.
Mobility ideas are easy to imagine: and costly to get wrong. MAAV NeoLab lets AI agents build and break synthetic scenarios, giving humans deterministic evidence before expensive real-world pilots.
One request. Many sites. Capability resolution for WebMCP agents.
A cloud-native collaborative studio for humans and AI to work together.
Your story is unique; AI helps you tell it. An agent that writes job applications out of things you've actually done — every sentence cited, and it asks you instead of inventing.
Whale Call connects travelers across 7 Caribbean islands with live water taxis & boats. Discover ports, book island-hopping trips, and stay safe with smart, real-time maritime dispatch.
Native Cloud AI operator running on Google Cloud Run that seamlessly executes 11 Google Workspace services directly inside Google Chat using Antigravity Engine & Model Context Protocol (MCP).
Trust infrastructure for economic AI agents: preserve human intent, verify evidence, bound authority, and prove outcomes before and after an action.
