si-protocols

Hybrid tech-psychic protocols for Spiritual Intelligence — open-source tools to detect and safeguard against disinformation in metaphysical narratives.

Cybersecurity for the soul. Run locally on your own texts only.

Quickstart

# Clone and set up (requires Python 3.12+ and uv)
git clone https://github.com/lemur47/si-protocols.git
cd si-protocols
uv sync --all-extras
uv pip install en_core_web_sm@https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl
uv pip install ja_core_news_sm@https://github.com/explosion/spacy-models/releases/download/ja_core_news_sm-3.8.0/ja_core_news_sm-3.8.0-py3-none-any.whl
pre-commit install

# Analyse a text file for manipulation patterns
uv run si-threat-filter examples/synthetic_suspicious.txt

# Map claims and structure in a text
uv run si-topology examples/synthetic_topology_suspicious.txt

# Run tests
uv run pytest

Quick-check (no install)

Don't want to install Python? Upload skills/quick-check.md to a Claude Project and paste any text — you'll get an instant structured analysis across all seven dimensions. See the file for setup instructions.

What this does

The threat filter combines two analysis layers:

• Tech layer — NLP-based detection across seven dimensions: vagueness patterns, authority claims, urgency/fear triggers, emotional manipulation, logical contradictions, source attribution analysis, and commitment escalation. Markers span six tradition-specific categories (generic New Age, prosperity gospel, conspirituality, commercial exploitation, cult rhetoric, fraternal/secret society).
• Heuristic layer — probabilistic dissonance scanner (placeholder for future biofeedback integration)

Output is a 0–100 threat score with a breakdown of what triggered it.

Topology analysis

The topology module extracts individual claims from a text, classifies each along four axes (testability, source verifiability, domain coherence, rhetorical role), and builds a layered graph showing how pseudo-scientific, true, and indeterminate claims relate to each other. Output is an SVG visualisation or JSON structure.

Project layout

src/si_protocols/
  threat_filter.py    # Hybrid NLP + heuristic threat scorer
  markers.py          # Disinformation marker definitions
  output.py           # Rich and JSON output formatting
  topology/           # Fractal-topology claim analysis and graph building
app/
  main.py             # FastAPI REST API (POST /analyse, GET /health)
  schemas.py          # Pydantic request/response models
skills/               # Claude Project skills (zero-install analysis)
site/                 # Astro documentation site
tests/                # pytest suite
examples/             # Synthetic sample texts (never real material)

REST API

uvicorn app.main:app --host 127.0.0.1 --port 8000

Local-only FastAPI server with POST /analyse and GET /health. Interactive docs at /docs.

Dev

uv sync --all-extras
pre-commit install
uv run pytest                 # Tests
uv run ruff check src/        # Lint
uv run pyright                # Type check
opengrep scan --config auto --error src/ app/  # SAST scan
osv-scanner scan source --config=osv-scanner.toml --recursive .  # Dependency vulnerability scan

Docs

• CLAUDE.md — Commands, architecture details, code style conventions
• docs/STRATEGY.md — Mission, audience, two-domain and two-channel strategy, roadmap overview
• docs/ROADMAP.md — Mid-term plan: topology roadmap, two-domain web presence, web demo, Chrome extension, note.com launch

Disclaimer

This tool is designed for local use on your own texts only. We do not host, collect, or analyse third-party, copyrighted, or channelled material. All example texts in this repo are synthetic.

Licence

MIT