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 autonomous B2B inbox agent turning Gmail orders into grounded, reviewable operations.
Google ADK + Gemini 3.6 Flash agent swarm with long memory autonomously sources, publishes, and moderates a Nostr travel network, turning tourism into education funding.
“Before you build, know what you affect.”
Agent Zen Garden is a WebMCP playground where AI agents design websites through real browser tools. An agent chooses a layout, writes the CSS, and publishes a live design humans can review and refine.
A family health record that reads itself — an agent files every lab report and prescription, then finds the duplicate medicine and the slow drift no single document shows.
A self-hosted, source-available Stripe store you own catalog, cart, SCA-ready checkout, orders, and field-level RBAC.
A 3D Nintendo Switch cartridge shelf and arcade gallery, built with Three.js. Browse my Switch game collection as an interactive 3D cartridge shelf.
Prove your AI agent is trustworthy while revealing nothing you don't need to. VeilPoint uses Midnight ZK circuits to verify AI security policies without leaking attack traces or customer PII.
An autonomous agent that helps film studios track blockbuster campaigns and filter bot traffic in real-time using Gemini 3.5 & ClickHouse Cloud.
Corroboration dies to Sybil attacks — one person faking a crowd. Quorum keeps an allegation sealed until N independently-verified reporters name the same person. Anonymous; independence proven in ZK.
Bringing AI Education Beyond the Internet.
A companion for panic attacks and the nights that won't settle. Crisis tools free forever, no account wall. Sleep tracks that end in silence, never applause. Not a cure. A witness.
Real-time environmental data, AI-powered risk intelligence, and actionable insights to help protect our planet.
Live vendor due diligence that turns SerpApi evidence into an explainable go, caution, or hold decision before you commit.
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
An AI agent that can't misbehave — a real Midnight ZK contract blocks any spend that breaks policy or fails a private reputation check, without ever revealing the score itself.
Let an AI agent spend your money under a policy it can prove it followed without ever revealing the policy, your spending history or your recipients on-chain.
SignalShield helps social platforms detect harmful automated amplification by combining bot, content and coordination signals with explainable, human-led moderation.
Multi-agent governance runtime for research labs — policy-enforced access control, automatic failure recovery, and auditable decisions on Gemini 3.5, ADK, and Cloud Run.
AI agents are your biggest audit risk. Can you prove they only saw what they should? Keyhole enforces data scope across Gmail, Slack, Salesforce & 6 more - with cryptographic proof.
“Ancient Wisdom, Modern Astrology.”
The AI suggests answers from redacted text; Midnight proves your disclosure policy was enforced.
nmemo gives student and community teams a shared, cited context layer so their AI agents start every task with the right project knowledge.
AgentReady turns a brand's product catalog into a structured, evidence-backed knowledge layer that AI shopping agents can actually reason over — and shows the brand exactly how ready each product is.