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 swarm of 300+ AI agents stress-tests your MCP server with realistic and adversarial users, then scores every failure, ranks it by severity, and files the real bugs automatically.
When DataHub says a column exists but PostgreSQL says it doesn't, Sidq blocks the agent — and writes the proof back through DataHub's official MCP tools.
An AI-native DataHub control plane that detects, quarantines, reconciles, and audits risky order and payment operations.
Finds documentation in your DataHub that stopped being true, proves it from DataHub's own change log, and fixes it behind a hash-verified human gate. 77 datasets scanned, zero false verdicts.
Autonomous Data Incident Commander powered by DataHub context graph.
DataHub maps where data goes. Covenant remembers the agreement governing every use—and traces what must change when the agreement does.
DATA ASSET LAUNCH RADAR FOR DATAHUB A proactive governance layer that turns the DataHub graph into a live radar.
Ratchet walks git history to find security regressions others miss — links every one to its cause, checks if it's still live today, and writes the evidence straight into DataHub's graph.
Find metadata debt, approve one safe repair, and prove the result in DataHub.
Detect, explain, and safely remediate production ML data failures using DataHub metadata, lineage, AI agents, and human-approved incident response.
Catalog health ≠ data health. A DataHub agent that A/B-audits metadata vs SQL freshness on nyc-taxi, proves silent staleness, then writes Incidents, Documents, and tags back into the graph.
Production workspace for data engineering
Makes DataHub your team's institutional knowledge base: an agent investigates once, and the answer lands in the catalog where the next person already looks.
An AI agent that catches the silent data bugs every monitor misses: a column's meaning flips but the numbers don't. It reasons from the code and writes durable contracts back into DataHub.
Ariadne is a decision governance layer for high-risk ML systems: models provide evidence, deterministic rules produce verdicts, and every decision is sealed and traceable.
ChainScope — Blockchair Multi-Chain Explorer
Context-aware AI software engineering platform powered by DataHub MCP & LangGraph for automated Clean Architecture FastAPI & Next.js generation with lineage & risk analysis.
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
An evidence-first AI incident response system for DataHub that uses MCP-verified investigation, requires human approval before write-back, and independently verifies every recorded incident.
AI agent that scans DataHub's ML lineage, flags stale/unowned training data, and writes findings back into the catalog.
See hidden consumers before a schema change ships, then generate a cited, backward-compatible migration plan instead of guessing from one repository.
Multi-agent incident response for DataHub. Detects failing assertions, walks the lineage blast radius, writes a structured incident back to the graph, and notifies owners in one Slack message.
Operational data agent: governed context in, approved action and durable memory out.
Faultline protects production ML before failures happen—tracing schema-change blast radius at the pull request, investigating silent model degradation, and writing governed findings back to DataHub.
481 – 504 of 612
