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:
Prove your degree without handing over your identity. (Beginner Track Focused)
An agent-native PC configurator where people and AI build the same PC together without sacrificing compatibility or trust.
An agent compares the stocks. You review the trade-offs. The save tool only appears after you approve.
Decurandi-w is a multi-agent AI solving clinician burnout. It synthesizes pre-visit EHRs, turns ambient audio into SOAP notes, and tracks per-agent LLM spend for secure, cost-controlled care.
FinalPick turns human choices between AI generated text and image option into reusable decision memory, while 6 WebMCP tools help agents prepare reviews without taking final authority away from people
Taboo makes WebMCP fun and reveals its disruptive promise: personal agents that act across the web, converse by voice, visualize insights, and bridge AI, AR, and the web.
A behavioral trust layer that checks what WebMCP tools actually do.
A self-hosted, source-available Stripe store you own catalog, cart, SCA-ready checkout, orders, and field-level RBAC.
FairShare helps roommates split shared belongings fairly. Private yes/no votes create a provably fair split up to one item, explain it plainly, and never store ballots.
Enterprise agents drop the case file. ContextRail carries it: one sentence in, 7 actions verified, 1 refused with the clause quoted and no approval can override it. The refusal is the product.
Transactional middleware that lets AI agents explore safely and makes only validated outcomes real.
Use LLM-powered WebMCP agents to discover and prepare tours directly with local operators—cutting out marketplace middlemen while keeping payment human-controlled.
SNIPR uses WebMCP to let AI agents safely query renovation assignments, inspect spatial room context, and propose actions while keeping SNIPR the source of truth.
A 3D Nintendo Switch cartridge shelf and arcade gallery, built with Three.js. Browse my Switch game collection as an interactive 3D cartridge shelf.
The live attention marketplace where AI-generated ads reward people for paying attention.
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.
Trust Gate : Verify every AI agent action before it becomes a real-world consequence.
Founder Scope is an AI-powered startup validation platform that helps founders analyze opportunities, competition, risks, and market potential. 🚀
Fair Split is expense-splitting that doesn't stop at tracking, one tap sends a real Stripe transfer that actually settles the debt. No more IOUs, no more reminders.
Prove you hit your fitness goal — without ever revealing your actual data — using zero-knowledge proofs on Midnight.
A zero-knowledge proof that your AI hiring decision followed the fairness policy, not that anyone got hired.
Turn company support knowledge into battle-tested AI skills. SkillMint learns procedures from solved tickets, guardrails from failures, and validates skills on unseen cases.
SURF Security Agent Control secures WebMCP actions with identity, DLP, human approval, credential isolation and audit , We are bringing Zero Trust to AI agents on the web.
A conversational shopping agent with dynamic state tracking and in-memory FTS5 retrieval, driving a 98% Hit Rate@10 and 0.728 MRR in just 2.29 turns.
