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
ATLAS is an autonomous engineering system that turns natural-language goals into enterprise-aware implementation workflows.
Renovate for breaking data changes.
Turns DataHub's raw metadata into answers a new analyst can actually understand.
Detects silent BCI decoder drift, raises it as a DataHub Incident, and runs a human-gated re-calibration that writes back to the graph.
ADA compliance on autopilot: an AI agent reads your DataHub catalog via MCP, runs real PDF accessibility scans, and writes verdicts back — daily, with evidence, so people never re-check a file.
Production-ML agent that watches your DataHub lineage graph, detects silent failures (stale data, schema drift, distribution shift), and writes incidents back so downstream agents inherit the context.
Autonomous deprecation campaigns for DataHub: evidence-backed dead-dataset sweep, human approval gate, catalog write-backs, owner-ping and cleanup-PR drafts, plus cost/ROI estimates.
Turn every risky schema edit into a DataHub-grounded, reversible change passport.
Keystone audits your DataHub catalog and publishes the missing governed context back. The same free text-to-SQL agent then jumps from 45% to 95% correct. Context is the lever, not model size
Know what your SQL change breaks — before you merge it.
Context before action. Receipts before trust. A DataHub agent that fixes metadata only after scoped approval and exact live verification.
Generate production-ready SQL from natural language using DataHub metadata and AI.
Context-aware AI agents for collectible retailers: DealerIQ uses DataHub to turn launch demand, inventory, fraud signals, and lineage into auditable purchase-limit decisions.
Autonomous AI agent using DataHub MCP & LangGraph to detect stale data, compute blast radius, write back metadata, and auto-generate dbt models & Airflow DAGs to heal data pipelines in real time.
Right to erasure, proven across the graph with DataHub lineage.
DataHub-aware canonical capability reuse routing for AI coding agents.
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.
Block risky schema changes with catalog-grounded evidence, compatibility code, and auditable DataHub writeback.
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.
Agent that walks DataHub lineage graphs to catch schema drift & PII exposure before they break production ML models.
A blast-radius-aware compiler that turns risky schema renames into DataHub-grounded migration bundles a data team can review and merge.
Renames a warehouse column without breaking what depends on it: reads DataHub lineage, writes dbt repairs across every affected repo, proves they build, and refuses when it cannot prove them safe.
The evidence-backed ML lineage archaeologist for DataHub that turns historical incident patterns into proactive risk prevention.
An evidence-first DataHub agent that reads ML lineage, blocks unsafe releases, and writes a deterministic repair receipt back to the model.
49 – 72 of 612
