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
A fare-prediction model's error metric creeps up over three days. No alerts. No failed jobs. Dashboard's green. This is a silent failure — the kind that costs money for weeks before anyone notices.
When data breaks, agents just restate the symptom. AgentsMeristem walks the DataHub lineage to the root cause, writes it back as an incident, and runs as a local 7B any agent can call over MCP.
Give DataHub a memory of past incidents: the agent surfaces an upstream candidate through MCP, writes it back, and recalls it instantly on recurrence.
When a dashboard breaks, the agent reads DataHub first.
From a broken dashboard to a verified repair: a DataHub-native incident agent that investigates, contains, fixes, tests, and hands off the exact evidence.
Catch silent ML failures before they cost you — an agent that traces DataHub lineage to flag production models an upstream change is about to quietly break.
An AI agent that reads DataHub lineage to predict which downstream report field breaks when an upstream schema changes — and writes the data contract back.
LineagePatch turns DataHub metadata incidents into evidence-backed impact analysis and reviewable code patches, with human approval before write-back.
What if every hiring decision made your AI recruiters smarter? We built a DataHub-powered multi-agent recruitment platform where AI agents learn, collaborate, and improve every hire.
A Slack-native agent that turns DataHub context into prioritized, human-approved metadata remediation plans.
When data consent changes, RevokeGraph finds every affected model, orchestrates an approved replacement, and proves the withdrawn data no longer reaches production.
Finds unmasked PII in your DataHub catalog, checks downstream lineage impact, and ships the fix as a GitHub PR — never as raw DDL. Closes the loop by writing governance state back to DataHub.
The ML lineage agent that just can't stop staring.
Every data change ships with proof, not confidence. ContextSeal uses DataHub context to block risky schema changes and generate safe, reviewable migration packages.
Test and repair risky dbt schema changes with DataHub
Stops silent data changes before they break production ML—using DataHub context to score blast radius, propose a constrained repair, validate it in dbt, and write the decision back.
AI-powered educational platform for Ethiopian students. Complete textbooks, past exams, and personalized tutoring in Amharic & English. Offline-first for low-connectivity areas.
AI agents write to your catalog, but nothing verifies they're truthful. EPISTEME is an autonomous trust layer—a Red/Blue agent pair that catches false metadata against real evidence and self-heals.
AI agent that investigates a real email corpus, flags the abnormal, and writes each finding back into DataHub as a walkable chain of custody — evidence, SQL, lineage, down to raw emails.
A model that scores 100% is usually cheating. Hindsight uses DataHub column lineage to prove a feature knew the answer before the decision was made, and blocks the release.
DataHub context becomes operational proof.
A metadata-aware agent that reads DataHub lineage, ownership, and quality context to explain impact and recommend safe, actionable next steps for data teams
A desktop coding harness for open-weight models (DeepSeek, Qwen, Kimi, MiniMax). Connects DataHub's MCP so agents read real schemas & lineage before generating code — every edit gated by your approval
A natural language to SQL agent grounded in live DataHub metadata. Ask a question in plain English, get real SQL run against messy retail data, complete with data-quality context baked in.
25 – 48 of 612
