Skip to content

Releases: BOOK318/OSSsystem

v0.1.0 — Initial public release

03 Jun 08:24
@BOOK318 BOOK318
v0.1.0
06a694f

Choose a tag to compare

View all tags
v0.1.0 — Initial public release Latest
Latest

What is this

Privacy-first Traditional Chinese / English AI safety guardrails for LLM-assisted workflows.

Deterministic rules run in front of every LLM call: private data is filtered before the model sees it, replies must quote approved knowledge, and risky actions require a human.

Highlights

  • Zero production dependencies — plain Node.js stdlib only.
  • 2,000+ assertions across 36 test files.
  • 30-second demo — node examples/quick-demo.js (no API key, no install).
  • Maintainer automation guardrails — PR risk classification, secrets/PII scan, unsafe-automation detector.
  • PR guardrails CI — secrets/PII scan runs on every pull request before any LLM step.
  • Red-team case pack — 10 adversarial scenarios for prompt injection, secret leakage, unsafe auto-merge, and more.

Quick start

git clone https://github.com/BOOK318/OSSsystem.git
cd OSSsystem
npm test                       # 36 test files, zero install
node examples/quick-demo.js    # full pipeline, no API key

Contributing

8 good first issues are open — all self-contained, one PR each. See CONTRIBUTING.md.

All fixtures must use fake data only. No real secrets, PII, or customer data.

Assets 2
Loading