Nemesis is the public-facing investigative interface as the result of Operation Diponegoro, initiated by Abil Sudarman School of Artificial Intelligence. We ingest millions of rows of procurement data, surface anomalies, and make the findings legible to citizens, journalists, and policymakers.
End the vampire ball.
| Asset | Status | ETA |
|---|---|---|
| Dashboard URL | 🟡 In progress | 17 April |
| Fine-tuned model | 🟡 In progress | ? |
Stay tuned.
Download SIRUP raw jsonl dataset (analyzed by GPT-5.4)
Download SIRUP dataset SQL Ver (analyzed by GPT-5.4-mini)
Stay tuned
Download and unzip the raw dataset, then convert it to SQLite:
# Convert raw jsonl data / sql data
# Place the resulting .SQL file at the expected path:
mv dashboard.sqlite backend/data/dashboard.sqlite
The backend expects the database at backend/data/dashboard.sqlite.
1. Start the backend
cd backend
npm startThe backend runs on http://127.0.0.1:3000.
2. Serve the frontend (in a second terminal)
cd frontend
python3 -m http.server 8080Then open http://127.0.0.1:8080 in your browser.
The frontend is preconfigured to call the backend at http://127.0.0.1:3000/api.
- No frontend build step required — plain HTML/CSS/JS.
- If
backend/node_modulesis missing, install dependencies:
cd backend
npm install- For development mode with hot reload:
cd backend
npm run devBackend config is loaded from backend/.env. Default values:
PORT=3000
CORS_ORIGIN=*
SQLITE_PATH=data/dashboard.sqlite
AUDIT_DATASET_DIR=dataset
GEO_ROOT_PATH=seed/geo