Skip to content

package sentinel

Persistent agent loop for packaging excursions.

Code Demo Cerebral Valley

Core trick

Runs a managed Gemini agent loop over strip-map and sensor traces, drafting cited containment packets gated by engineer approval.

Tags

robotics/hardwareagents

Description

Persistent agent loop for packaging excursions. Monitors visual strip maps, sensor traces, travelers, and tester bins to automate post-alert investigations and draft cited containment packets for engineer review. hosted and accessable here: https://package-sentinel.pages.dev/
natask/google_hack★ 00 forksPythonCreated May 23, 2026 · last push May 24, 2026

README excerpt

# Packaging Sentinel

A managed-agent and deterministic replay framework for semiconductor advanced packaging and final-test excursion investigation. 

This repository leverages Google Cloud's **Agent Platform** (running hosted Gemini models like `antigravity-preview-05-2026`) and static, physics-defensible data generators to identify, isolate, and recommend human-approved containment for manufacturing drift.

---

## 🚀 Quick Start

### 1. Requirements
* Node.js (v20.6+ recommended; uses native `--env-file` flags)
* Python 3.9+
* Google Cloud SDK (`gcloud` authenticated, if running live hosted agents)

### 2. Installation
Install NPM dependencies for the web dashboard and Cloudflare Workers API:
```bash
npm install
```

### 3. Generate Simulated Datasets
Synthesize physics-coherent semiconductor datasets (covering reflow, underfill, and electrical testcell scenarios):
```bash
python3 scripts/generate_osat_watchtower_data.py all
```

### 4. Run Deterministic Replays & Evaluation
Run the local state-machine simulation and score the accuracy of findings against the scenario ground truth:
```bash
# Replay and score the default scenario
python3 scripts/run_watchtower_simulation.py --scenario reflow
python3 scripts/evaluate_watchtower.py --scenario reflow
```

### 5. Launch the Dashboard
Serve the interactive frontend UI locally:
```bash
python3 scripts/managed_demo_server.py
```
Open your browser and navigate to `http://localhost:8000` to interact with the visual telemetry, explor

Team