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:
A 100% local, agentic research operating system featuring autonomous deep research, Cornell notes, STEM simulations, dual host podcasts, and interactive thesis viva defense.
Every Agent Run is guilty until proven safe.
Privacy-preserving clinical outcome prediction across 5 hospital silos, orchestrated by an autonomous AWS Strands AI agent with zero raw patient data leakage.
Rival banks' AI agents negotiate the terms of a joint fraud investigation, then compute the answer in a clean room neither side can read, catching the ring together without sharing one record.
Prove you drove safely without revealing where you drove. DriveProof turns attested private telemetry into a ZK compliance receipt on Midnight.
An AI security analyst that investigates threats, detects anomalies, and protects your website through WebMCP.
An agentic system that finds every legal front to reduce or erase a medical bill and files the paperwork itself.
GoalThread turns fragmented AI agent tasks into goal-aware threads! Merging related work, isolating unrelated tasks, and forking cleanly when your goal shifts.
Don’t trust the first patch. Prove the best one with parallel Nemotron repairs and reproducible execution evidence.
A multiagent that can coordinate and reuse what it learns.
A Kill Switch for AI Agents that blocks work a task never authorised — not because the action looks dangerous, but because this run wasn't allowed to do it.
Human-in-the-loop approval and full audit trail for AI coding agents with filesystem access — with a live bypass-detection layer.
Privacy-preserving voting dApp on Midnight — votes stay anonymous via ZK proofs. Same idea could power anonymous misconduct reporting. My first hackathon, built solo from zero blockchain experience.
Autonomous night-shift SRE fleet on Google's Agent Platform — five ADK agents detect, diagnose, contain and verify incidents across Grafana while you sleep.
Verify sensitive HR claims with zero-knowledge proofs, without revealing the underlying data.
An autonomous AI agent that rescues messy, risky datasets—detecting quality and privacy problems, safely fixing them, verifying the results, and delivering trustworthy, ML-ready data.
A source-grounded payment agent that hard-blocks changed bank accounts until deterministic controls and a real human clear a signed release.
Searcharis watches every deploy, catches search regressions, opens the right GitHub issue, and closes it only after fresh evidence proves the fix.
Turning informal WhatsApp, text, call promises and overdue trade credit ledgers into recovered cash, with unforgettable memory using browser-native AI agents and the WebMCP standard.
An autonomous, source-grounded agent that turns estate documents into a safe Alberta action plan, tracks deadlines, updates the case, and prepares review-ready notification packets.
A cross-chain attestation solvency engine on Midnight Network that lets users prove reserves and creditworthiness across chains, without exposing balances, liabilities, or wallet history.
Private Pet Vaccine Pass uses Midnight ZK proofs so owners can prove a pet’s rabies vaccine is valid through a required date—without revealing the medical record.
When a fridge fails, ColdClock gathers the evidence, stops for the pharmacist's decision, then finishes the replacement and delivery by itself. Zero operator clicks, with a signed receipt.
Password login on an existing physiotherapy portal replaced with a Midnight ZK proof. Clinicians verify without revealing. A breach of the server yields no credentials, because there are none.
