Skip to content

SaarthurR/Diggity

Repository files navigation

Diggity — The Digital Archaeologist

Point a camera at an object and get back a structured archaeological reading of it: a specific name, estimated age, likely civilization, material, purpose, probable origin, and why it matters — generated by GPT-4o vision and presented as a field-notes dossier.

Built as a full-stack TypeScript app: React 19 + Vite front end, Express API, Drizzle ORM for persistence, and the OpenAI API for artifact analysis. Themed as a digital excavation tool, originally an FLL "Code-Linker" project.

What it does

  • Scan an artifact — upload or capture an image; POST /api/analyze sends it to GPT-4o with an expert-archaeologist system prompt.
  • Structured results — the model returns typed JSON: name, age, material, purpose, location, civilization, civilizationPeriod, whyItMatters, and a confidence score.
  • Excavation pipeline UI — a staged "dig" interface (RobotExcavationPipeline, Scanner) walks the analysis from capture to report.
  • Language insights — supporting analysis surfaced alongside each find (LanguageInsights).

Stack

Layer Tech
Front end React 19, Vite, Tailwind CSS, Radix UI
Server Express, TypeScript (tsx)
Data Drizzle ORM (shared/schema.ts)
AI OpenAI gpt-4o (vision)

Layout

client/    React app (components, pages, assets)
server/    Express API — routes.ts holds /api/analyze
shared/    Drizzle schema shared by client and server
script/    build pipeline

Getting started

npm install
export OPENAI_API_KEY=sk-...
npm run dev        # tsx server + Vite, http://localhost:5000

npm run build produces a production bundle via script/build.ts.

About

Digital archaeologist — snap an artifact and GPT-4o vision returns a structured dossier (name, age, civilization, significance). React 19 + Express + OpenAI.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages