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:
Decision intelligence for film & TV IP — research, evidence graph, deterministic scoring, and drift monitoring.
Data quality tools watch your data. Nobody watches whether the documentation is still true. This open-source DataHub agent does, judging context, not schema diffs.
Buyer and seller agents turn live evidence into safe software decisions, powered by CockroachDB and Amazon Bedrock.
Privacy-first AI that detects human risk, uses DataHub to trace the data and model behind predictions, and explains the evidence and recommended action.
When a live stream degrades, this Gemini agent triages Grafana telemetry through a deterministic runbook, remediates what it can, and refuses to act when it can't.
Twin is chaos engineering for data platforms. It reads your Datahub graph, breaks a real copy of your warehouse, checks whether the catalog predicted the damage and writes the verified truth back.
Catch AI agents breaking their own rules. Mutiny finds verified tool-call policy violations and locks them as FAIL→PASS regressions so unsafe agent behavior can’t silently ship.
An AI-powered data engineer that understands metadata, diagnoses data issues, and automates reliable data workflows.
Moving to Japan means paperwork with invisible deadlines and a language you need on day one. Ittekimasu dates your visa checklist to your move and teaches the Japanese you'll use at the ward office.
Describe a feature once. Chuchube plans it into a graph, runs coding agents in parallel, and merges the work back in dependency order. An AI engineering manager, not another AI coder.
An agentic reliability control room using DataHub lineage, quality, and ownership context to stop healthcare data and ML pipeline issues before they impact clinical operations.
CommitmentOS doesn't just find the commitments in your email — it schedules the work, replans around changes, and verifies that the tasks are actually done.
Govern every AI action. Trust nothing by default. Zero-trust governance layer for AI agents with policy, reputation-gated, delegation-scoped, and written to a tamper-evident audit chain.
Two dashboards disagree about revenue. RIFT proves exactly why it rewrites the SQL, executes it, and measures what each clause is worth in dollars — then writes the answer back to DataHub.
DataHub-grounded schema migration agent with deterministic policy, counterfactual dbt proof, immutable safety cases, and post-merge verification.
Speed is nothing without control. To optimise for low latency alone misses the most important part of Physical Ai: correctness. I reduce VLM from ~4Sec. to 33ms gesture input + 500ms per. observation.
Turn a whiteboard photo into a validated dbt + Airflow PR — grounded in DataHub via the MCP Server, tested in DuckDB before merge, with column-level lineage written back to the catalog.
A column gets dropped, a serving model goes quietly wrong, nobody notices for weeks. Tether blocks that PR. When it misses one, it writes the missing lineage edge to DataHub, and stops missing it.
MediRAG — AI-powered medical document analysis and RAG system delivering accurate, source-backed answers from uploaded medical records.
An agent that reads your DataHub catalog every day, writes what it found in four voices people actually read, and writes it back so the next person inherits it.
Veristock is hotel operations infrastructure with AI-powered intelligence built on top.
DevCloudDesk is an all-in-one server control center with an AI-powered terminal, one-click actions, deployments, monitoring, cron jobs, security, and service management.
Retirement Conductor uses DataHub to find every downstream consumer, migrate and validate changes, then delete a legacy field; or stop when fresh evidence changes.
An agent that finds the silent failures in your dbt warehouse — green build, green tests, wrong revenue — proves them empirically, and hardens against them.
