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 code generation agent that establishes what it knows before it writes. Finds what a schema change breaks, generates and runs the fixes — or declines, and names the metadata that's missing.
Autonomous data governance agent using fine-grained lineage to detect renamed PII columns and generate secure dbt masking code via human-on-write principles.
Detects ML features silently broken by renamed, dropped, or retyped warehouse columns — before they corrupt production models. Built on DataHub's schema, ML metadata, and MCP Server.
The blast-radius gate for data model PRs. Missing lineage never returns SAFE.
Compliance tools manage documents. PROVE IT uses DataHub to determine whether an audit claim is actually provable from live operational evidence, not just written policy.
janus is an ML deployment gatekeeper that reconstructs whether your training data was healthy at the moment you trained, and writes the evidence back into DataHub as a Model Passport.
An autonomous agent using DataHub metadata context to detect untagged PII, generate masked dbt transformation models, and write governance tags & assertions back to the Context Graph.
Mama said, life’s like a box of chocolates. STOP! You do know DataHub labeled it underneath, don't you?
Stop Code Slop, put your agent on a leash and know where your code is going.
Ask questions in plain English and let DataQuery AI turn them into SQL instantly, identify relevant data, and explain the query—making data analysis faster and accessible to everyone
An AI agent that connects to DataHub, understands your organization's schemas, lineage, ownership, datasets, pipelines, and ML models, detects problems, explains their impact, and executes fixes.
An AI safety agent that detects corrupted race telemetry, switches to a trusted backup, and uses DataHub lineage to trace downstream impact.
A prompt-injection immune system for DataHub: excises jailbreak payloads hidden in catalog metadata, repairs the graph, proves 12/12 gone in 8 ms.
Turn DataHub query history into schema-validated dbt Semantic Layer metrics - so AI agents stop guessing.
From a breaking data change to governed, merge-ready code — DataHub finds the hidden consumer, ContextTwin repairs it, Replay proves it, and the mapped owner approves it.
AI-powered multi-agent workspace for YouTube creators
An AI-powered data reliability engineer that remembers past incidents, validates whether old fixes still apply, learns from every investigation and write lessons back to Datahub for future agent use.
An explainable paper-first trading agent using DataHub context and CockroachDB agentic memory.
DOPPEL turns sensitive production datasets into privacy-safe synthetic twins that preserve useful structure and relationships, using DataHub context for governance, lineage, and verification.
DataShield Guardian is an autonomous AI agent that protects ML systems from data leakage, PII, drift, and schema failures—tracing risks through DataHub lineage and taking action before models break.
RegLens reads a bank's DataHub graph to find what a new regulation touches, costs acting now vs deferring vs minimum compliance, and writes the decision back so the next team inherits it.
The DataHub-powered agent that blocks dangerous dbt changes, proves a real repair, gates release on owner approval, and writes reusable knowledge back to DataHub.
An AI agent that reads DataHub's MCP Server to catch AI agents violating data-access policy — then writes the violation straight back to DataHub and opens a GitHub issue automatically.
Close the schema-change loop with DataHub-grounded impact, action, and memory.
361 – 384 of 612
