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:
SEARCHOps is an autonomous research agent returning reports where every claim is cited, quoted, and cross-checked across sources—powered by Nebius AI Studio, with Tavily for web search.
The Netflix for news powered by Agentic AI
This project combines enterprise knowledge graphs and LLMs to investigate vehicle recalls, analyze complaints, trace supplier relationships, and deliver evidence-backed insights.
RECLAIM uses AI to turn consumer complaints into clear action plans by organizing evidence, finding relevant rules, and guiding users from problem to resolution in one place.
An evidence-grounded job-search agent for LLM and Agent internship seekers in China: every claim opens to its source.
Everyone automates the safe edit. Molt makes the dangerous one: the database, the dependency, the dead app. It proves the change can't break production on your real data, then ships it hands-off.
Learn any career by actually working it. Build a company, explore a 3D office, and team up with others and AI coworkers who assign real tasks, coach you, and give feedback as you improve.
PSCYPHER turns scattered FIRs, call records and bank transfers into one evidence graph that a tool-calling Nemotron agent can interrogate — and every claim it makes is citation-checked.
Your own AI agent, forged from a single command. Build custom AI agents without writing a line of code. Describe it. AgentForge builds it. From idea to working AI in one command.
Orion is a junior AML investigator that lives in Linear. Hand it an alert — it builds the transaction graph, writes up what it found, and waits for your review. Push back in the comments.
AI-powered multi-agent system that automates the complete fraud investigation workflow.
GitLab Duo-native autonomous SRE: Ingests production bugs, verifies code patches in isolated sandboxes, and auto-merges safe fixes in under 60s with full risk & carbon governance.
Find a little joy along the way. JoyWalk turns an everyday route into a chance to slow down, breathe, and notice what’s around you.
Underwatch helps SWEs catch unauthorized access, trace potential data leaks, and verify security safeguards by comparing AI coding agents’ reported actions with independently observed system activity.
Alexa+ meal planner that hits your macros, verified by USDA
Stop guessing why videos go viral, VIOS reverse engineers 10,000+ videos into instant visual memory search, real retention blueprints, and hidden content gaps competitors missed.
Mirage safely attacks you first with personalized scam drills, then guards live calls, verifies cloned voices, and hunts real scammers.
Kairos turns a plant's scattered maintenance records into cited answers, early warnings and pre-job briefs, so teams decide on evidence instead of memory.
Turn any syllabus into a personalized learning journey with AI-powered curriculum mapping, smart topic sequencing, curated resources, and personalized quizzes to track measurable progress.
An explainable AI-powered disaster preparedness platform that uses knowledge graphs and agentic AI to deliver personalized learning, risk insights, and emergency response guidance.
An AI security team powered by NVIDIA Nemotron on Nebius: finds vulnerabilities, proposes patches, and tests fixes in isolated sandboxes—all through a developer CLI and MCP server.
Simplify Legal. Preserve Meaning. Verify Every Fact.
A secure enterprise AI vision agent that uses OpenCV 5 and AWS to analyze visual data, reason over findings, and trigger intelligent actions with human oversight.
