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 AI Powered Zero Trust IAM agent that remembers past access descisions to provide smarter, consistent, and explainable cloud access recommendations
It maps a project's files to the claims they support in DataHub, then an AI agent reads that map and reports which claims the evidence proves. When it can't tell, it says so instead of guessing.
Give it a project description and its demo video. It watches the video and makes a short narrated clip showing which claims the demo actually proves, which it skips, and which it contradicts.
Privacy-first hiring powered by AI, Zero-Knowledge Proofs, Compact Smart Contracts, and Midnight, enabling anonymous qualification verification with candidate-controlled identity disclosure.
Turn complex tender documents into structured, traceable requirements with page-level citations—helping bid teams catch omissions early and submit with greater confidence.
Five AI agents diagnose outages together, each specializing in different data. When they disagree, they negotiate. Built on Qwen Cloud and Alibaba Cloud with a live Terminal UI.
Repetita Gravity consolidates accidental semantic repetition around each idea’s logical centre—while preserving intentional structure, unique content, evidence, and context.
Money habits kids can practice: one weekly parent-child routine for earning transparently, then choosing how to Spend, Save, Give, and Grow.
Turn yourself into the ultimate AI harness. In one click, Punchbacks turns any app bug into a reproducible test, live preview, browser-verified fix, and evidence-backed pull request. Punchback bugs!
AI can generate a patch in seconds; the question is whether it is correct or merely lucky.
An abstraction layer that transforms system design into executable context for AI coding agents. Eliminate hallucinations and keep parallel agents synchronized through a single source of truth.
AI-powered live-commerce capture that verifies sales, matches real products behind generic listings like “Item on Screen 147,” and produces live KPIs, evidence and fulfilment-ready records.
Turn one story prompt into a continuity-locked six-shot film using Qwen Cloud for direction and keyframes, Wan for motion, human approval gates, and an inspectable production ledger.
Drydock lets coding agents safely manage real infrastructure by testing changes on an isolated clone first and only applying them after verification and human approval.
OpenDissertation helps you understand dissertations faster.
Your app died. Your data didn't. Anastasis watches a 2-min screen recording, reads your export, and Codex rebuilds the app you actually used, with data migrated, live on a URL you own.
The AI engineering partner that unifies security, compliance, testing and verified remediation—compressing weeks of assurance work into minutes.
AI reads. Government data verifies. A human decides.
ZK-Whistleblower is a Midnight DApp for anonymous reporting with cryptographic proof of document authenticity.
Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, enabling AI to safely call real business capabilities under permissions, audit, and governance controls.
Catches silent ML failures — target leakage, stale upstream data — before they hurt you, by reasoning over DataHub's lineage graph. Discovers risk itself, writes fixes back as real PRs.
An open-source, AI-search-ready B2B industrial commerce stack that turns complex catalogs into discoverable product knowledge, with no-code CMS, instant search, RFQs, and production-grade deployment.
Five specialist Qwen agents review a real KiCad board via MCP and debate conflicts under a Moderator. Burns 2.5× more tokens than one big agent — and costs 2.9× less. Zero hallucinations.
Agentic memory as a distributed SQL problem — transactional, temporal, self-correcting memory on CockroachDB + AWS.
