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
Cloud architect building AI agents on Google Cloud and AWS. Holds many Professional GCP plus AWS certs. Multi-time hackathon prize winner.
Get what you want for less CO2. We optimize products and shipping to lower emissions and cost while meeting your delivery.
AI-powered software development intelligence platform that transforms GitLab merge request data into actionable insights for engineering teams.
CloudSage is an AI Ops Oracle that reads your logs, detects hidden patterns, and predicts tomorrow’s failure risks using Raindrop SmartComponents and a Vultr-backed risk engine.
Upload a receipt photo. Nova 2 Lite extracts the data and infers the workflow. Nova Act opens a cloud browser and fills the real expense form. Receipt in, expense submitted out.
An interactive crash-autopsy workstation that preserves the final seconds of container telemetry and helps developers investigate why Python applications fail.
AI proposes recovery for failed PayPal subscriptions; merchant Approves; live sandbox capture proves recovered cash - not simulated webhooks.
A quality gate for AI travel agents: Qloo catches wrong-city and off-taste restaurant picks, then repairs the list. Same restaurant, two tastes: Prado fails a Radiohead fan, passes a Kendrick fan.
Phone photo in, OpenCV triage out. LookAgain uses vision metrics to pick the next tool—retake, compare, or bounded diagnose - across LEDs, brakes, and leaf spots. Bedrock + SIFT on AWS COOL.
StepClear uses Ring camera footage and Amazon Bedrock AI to flag potential doorway obstructions, helping residents keep accessibility routes in view through human-reviewed assessments.
A provenance and reliability gate for Codex-written code. DiffProof links each patch to its Codex session, replays tasks in clean worktrees, and blocks merges that fail adversarial tests.
Every AI-generated data change gets a DataHub-backed metadata lease. Before merge, ContextLease rechecks schemas, tags, lineage & owners - if context drifted, the PR is blocked.
RelayGuard gives incident-response agents crash-safe memory, so they can resume across failures, reject unsafe precedent, and prevent duplicate remediation actions.
SceneLedger turns changing source documents into source-linked training videos, detects stale scenes when instructions change, and regenerates only what is no longer accurate.
TruthExpiry prevents stale Slack answers by using real-time search and MCP evidence to find the current valid answer, explain what changed, and ask the right owner to confirm it.
FailureDNA gives incident-response agents persistent memory of what failed, what worked, and when a past fix no longer applies - USE, INSPECT, or AVOID - before Qwen acts on Alibaba Cloud.
Global scarcity engine for game drops, ticket presales & fan events - Aurora DSQL enforces one worldwide inventory cap under flash-sale concurrency. Vercel + OIDC in prod.
An Orbit-powered MR gate that enforces architecture-layer rules and required-test policy -catching even transitive violations no single-file review can see - before a merge lands.
An autonomous DFIR agent that investigates a Windows intrusion end-to-end, then adversarially verifies every finding. Every finding cited, every action audited, zero hallucinated evil.
Who watches the MCP agents querying your Splunk data? AgentSight does - native Splunk observability for AI agents: real MCP audit logs, agent-specific detections, and splunklib.ai investigation.
A Gemini + Fivetran agent that finds where personal data spread, prepares safe cleanup actions, requires human approval, and produces an audit report.
Turn messy GitHub bugs into proof: evidence packet → Lark workflow execution → managed issue comment. Live getlark REST/CLI + TrueFoundry parser, with graceful fallback when AI/MCP fails.
Every mod action gets a reason. Every appeal gets an answer. Log why from any post or comment, search a user's case file, and copy appeal summaries for modmail - built on Devvit for mod teams.
Put risky decisions on trial. Shadow Board challenges your thinking with six opposing roles, then gives a verdict, risk score, and 48-hour evidence test.
Stress-test any product or business decision against five overlooked stakeholders. Get a structured review plus a Decision Brief naming the real tradeoff, hidden assumption, and a clear reframe.