Skip to content
HackWinnerDBv0.1
Tech Stack Indextool

GitHub Actions

26 winning projects29 hackathons20262026
TechCommons Hacks V1 - Grand Winner

Reloop

Turn clutter into a climate win, the hyperlocal give-away map.

TechCommons Hacks · 2026

Artificial IntelligenceEducation
GitHub ActionsJavaScriptNode.jsOpenAI+8
Source pending review
ME
1st Place | Education

Mechanica — A Digital Museum of Ancient Chinese Machines

Four lost ancient Chinese machines reborn as physically-simulated, source-cited interactive exhibits — with a GPT-5.6 docent that refuses to hallucinate.

OpenAI Build Week · 2026

EducationCreative Tools
OpenAI CodexGitHub Actionsi18nextNode.js+13
Source pending review
Best First-Time Builder

Penetron

Penetron proves vulnerabilities instead of just flagging them: an AI agent exploits your running app to confirm what's real, governed end-to-end by UiPath.

UiPath AgentHack · 2026

Artificial IntelligenceEducation
AnthropicClaudeGitHub ActionsNode.js+3
Source pending review
1st Place Overall

RhetBench

RhetBench — a benchmark testing whether AI agents can persuade an NPC on a real-world topic. The character's hidden personality determines which persuasion stra

SWECCathon 2026 · 2026

Artificial IntelligenceEducation
FastAPIGitHub ActionsPythonUvicorn
Source pending review
SE
[AMD] Best Use of AI powered by AMD GPUs - 1st Place

Sentinel

Predict, Prevent, Intervene

Los Altos Hacks X · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
1st Place Team - $200 per team member

UrTurnIntern

One buried email. One missed deadline. One generic resume. That's how offers slip away. UrTurnIntern organises and uses AI to tailor resumes, prep interviews, a

SMU .Hack Enrichment Application Programme 2026 · 2026

Artificial Intelligence
GitHub ActionsNode.jsPostgreSQLReact+5
Source pending review
Dynatrace - 2nd Place

Karma — The Reincarnation Agent for Deprecated Services

A multi-agent system that learns a deprecated service's hidden contracts and haunts its replacement, catching silent regressions every test misses. Gemini + Ver

Google Cloud Rapid Agent Hackathon · 2026

Artificial IntelligenceEducation
FastAPIGeminiGitHub ActionsNext.js+6
Source pending review
SE
2nd Place

Sentinel

Predict, Prevent, Intervene

Cheesehacks · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
SE
2nd Place | Developer Tools

Sentinel

Predict, Prevent, Intervene

OpenAI Build Week · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
3rd Place

Dataset Trust Auditor

Know what's in your data before you train on it. Dataset Trust Auditor scores datasets across 8 trust dimensions — provenance, licensing, bias, quality — in sec

ZerveHack · 2026

Artificial IntelligenceEducation
ClaudeGitHub ActionsHugging FaceJavaScript+4
Source pending review
Dynatrace - 3rd Place

Heimdall: Autonomous Incident Response for Dynatrace

Autonomous SRE that watches your Dynatrace tenant 24/7, diagnoses production incidents from real spans and Davis CoPilot, and opens a pull request before your p

Google Cloud Rapid Agent Hackathon · 2026

Artificial IntelligenceEducation
DockerFastAPIGeminiGitHub Actions+11
Source pending review
3rd place

RoundZero

Interview Before it Counts.

Kindly labs weekly hackathon · 2026

Artificial IntelligenceEducation
GitHub ActionsPythonReactTypeScript
Source pending review
SE
Third

Sentinel

Predict, Prevent, Intervene

TillyHacks · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
MongoDB - 3rd Place

Sentinel Flood-Watch Agent

An AI agent that proactively monitors Accra's ecological sites using remote sensing data and advanced analytics, and alerts authorities and stakeholders to pote

Google Cloud Rapid Agent Hackathon · 2026

Artificial IntelligenceEducation
FastAPIGitHub ActionsJavaScriptPython
Source pending review
Best Use of Braintrust

ForkLab

ForkLab forks one distributed-agent failure into eight isolated Daytona worlds, then uses Braintrust to prove which interventions stop retry cascades—turning ou

Daytona HackSprint w/ Braintrust - SF, July 2026 · 2026

Artificial IntelligenceEducation
GitHub ActionsNext.jsPythonReact+2
Source pending review
Most Innovative Slack Agent

Handoff

Handoff is your Care Home Coordinator built inside Slack. It replaces sticky notes, binders, and text messages used in coordinating elderly care, where missed c

Slack Agent Builder Challenge · 2026

Enterprise
ClaudeDockerGitHub ActionsPython+1
Source pending review
[MLH] Best Use of Gemini API

Pulse - Smart Demand Signals

Convierte el histórico de compras de Inibsa en alertas comerciales accionables: a quién llamar hoy, qué vender, por qué motivo y con qué urgencia. Detecta deman

InterHackBCN · 2026

Artificial IntelligenceEducation
DockerElevenLabsFastAPIGitHub Actions+6
Source pending review
Best Use of Hermes -- Nous Research

Second Self

What if you could be in two places at once? Meet your AI twin who lives in your notch, works as you on your computer (via macos fast user switching), while you

YHack Spring 2026 · 2026

Artificial IntelligenceEducation
ClaudeElevenLabsFastAPIFirebase+12
Source pending review
SE
Best Use of AI - Mac Mini with Apple M4 chip

Sentinel

Predict, Prevent, Intervene

Hacktech by Caltech 2026 · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
SE
Best Use of VoiceOS and HypeScribe

Sentinel

Predict, Prevent, Intervene

SCU Hack-a-Stack - Endurance Track · 2026

EducationProductivity
OpenAI CodexDockerFastAPIGemini+18
Source pending review
Best Use of Gemma 4 || Gift card

Throughline

Atlanta serves a child care registry last refreshed in 2021 as current. Throughline measured the drift: 51.9%.

Hack RenderATL · 2026

Artificial IntelligenceEducation
FastAPIGitHub ActionsLlamaPython+2
Source pending review
DeFi Track

Latch

Give agents money, not your wallet. Latch is a private spending gate for AI agents, built with zero-knowledge proofs on Midnight.

Midnight Hackathon · 2026

Artificial IntelligenceBlockchain
GitHub ActionsNode.jsReactTypeScript+2
Source pending review
Honorable mention

AgentSentinel-MCP

Autonomous multi-agent red-teaming for clinical AI — turns every MCP-native adversarial test run into EU AI Act (Art. 9/12/15) compliance evidence.

Github readme generation · 2026

Artificial IntelligenceEducation
DockerFastAPIGitHub ActionsNext.js+6
Source pending review
Honorable Mentions

TrustedRisk Care Engine

A2A federation that decomposes one clinical prompt into a multi-specialist consultation: 16 sub-agents, 257 workflows, narrated dispatch, calibrated abstention

Agents Assemble - The Healthcare AI Endgame · 2026

Artificial IntelligenceHealthcare
AnthropicDockerFastAPIGitHub Actions+6
Source pending review