Semantic Tension Language

A calculable, universal standard for structuring knowledge. Human-readable. Machine-executable. LLM-native.

🛡

Traceable & Verifiable

Every statement can embed provenance, confidence scores, and temporal context. Know where knowledge came from and how much to trust it.

⚙

Calculable Tension

STL models knowledge as directional tension paths. Compute semantic distance, detect contradictions, propagate activation through knowledge graphs.

⚡

Token-Efficient

Compact syntax optimized for LLM context windows. Encode more knowledge in fewer tokens than JSON, XML, or natural language.

◆

Human-Readable

"STL syntax is intuitive: [Source] -> [Target] ::mod(confidence=0.9

See STL in Action

Basic Statement

stl-key">class="stl-anchor">[Einstein] stl-key">class="stl-arrow">-> stl-key">class="stl-anchor">[Theory_Relativity] stl-key">class="stl-mod">::mod(
  stl-key">rule=\"logical\

Causal Chain

stl-key">class="stl-anchor">[Heavy_Rain] stl-key">class="stl-arrow">-> stl-key">class="stl-anchor">[Urban_Flooding] stl-key">class="stl-mod">::mod(
  stl-key">rule=\"causal\

Explore the Ecosystem

Parser, CLI, MCP tools, and 6 domain schemas — everything you need to start working with STL.

View Tools

This website is AI-native. All content is authored in .stl files and served directly to AI agents at /.well-known/site.stl