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:
Autonomous procurement risk detection, zero-hallucination financial reconciliation, and Human-in-the-Loop governance on Google Cloud.
An autonomous agent that detects when business purpose expires, maps hidden dependencies, safely retires obsolete resources, and verifies active teams remain unaffected.
An agent that hunts funding for independent journalists while nobody is watching — it verifies every deadline against its source page and drops what it cannot confirm.
Investigation, case, and evidence management system powered by autonomous AI agents.
Built for the "Build Next-Gen AI Agents - All Things Agentic Hackathon" (Taskmaster Track).
Prove you're 18+ using zero-knowledge proofs on Midnight Network — no ID shown, no birthdate revealed, no data trail. Just a live, unforgeable yes at the door.
Prove that you meet job requirements without exposing your résumé or personal information.
An agentic system that separates Arabic text matches from historically valid authorial attestations using Gemini, Google ADK, and deterministic evidence verification.
Spend with freedom. Stay prepared. Reveal only what matters.
An AI agent that uses WebMCP to take passengers from flight cancellation to compensation.
A zero-knowledge permission layer for AI agents: every MCP tool call must prove it satisfies private authorization policy before execution—without exposing prompts, data, credentials, or rules.
An AI debate coach that challenges students to defend their reasoning instead of giving them answers.
Guardian Rail lets AI services verify 18+ eligibility with Midnight zero-knowledge proofs—unlocking access without collecting a birth date, ID, selfie, or permanent identity.
Company context and human control for engineering agents.
DeployGuard AI assesses repository readiness, detects security risks, applies controlled fixes, and verifies remediation with proven results—helping developers deploy safer software with confidence.
The regulatory desk a principal investigator doesn't have: agents that draft every US clinical trial submission, cite every claim to the CFR, and never miss a statutory deadline.
Three-agent pipeline that finds streaming QC anomalies in ClickHouse, diagnoses them with Gemini, and files real GitHub issues — no human in the loop.
QuietAid helps students prove scholarship eligibility with Midnight without revealing the sensitive personal circumstances behind it.
A Zero-Knowledge anti-deepfake platform that verifies whistleblowers' raw footage on the Midnight Blockchain without exposing their identity.
A privacy-preserving DevSecOps gate that proves a repository passes security policy with Midnight ZK proofs without revealing the underlying scanner findings.
Blind Bazaar: AI agents bid in live ad auctions without revealing their real numbers — Midnight proves the deal was fair, cryptographically, without ever exposing the private data.
AI pair programming that helps you learn to solve problems, not just copy solutions.
Fynura turns fragmented public-health evidence into verified, traceable intelligence, helping professionals, researchers and communities understand signals and act sooner.
SerpMe turns local market signals into evidence-backed business decisions and analyzing competition, demand, viability, financial scenarios, and space concepts for new ventures.
