Semantic layer
for AI agents
Define metrics once. Query them from Claude, Cursor, apps, or Python — using a lightweight semantic layer designed for agent workflows.
python-native • agentMCP-first • standalone or embedded • open source
What is Motley
Most semantic layers were built for BI tools. SLayer is built for AI agents that need predictable, structured, and reusable access to analytics logic.
SLayer provides a simple semantic interface that maps cleanly to LLM-generated queries while remaining powerful enough for real analytics logic.
Instead of generating fragile SQL, agents query a structured representation of metrics, dimensions, joins, and time logic.
This makes queries more reliable, reusable, and easier to reason about.
How It Works
Connect Your Data
· SLayer introspects your schema and creates semantic models automatically.
· Foreign keys become joins
· Columns become measures and dimensions
· Models are queryable immediately
Adjust models dynamically
Update models instantly through YAML or API without rebuilds or compilation steps.
Fast iteration for agent workflows and changing schemas.
Query via structured interfaces
Use the same semantic definition across every workflow.
One definition, reused everywhere
Why developers choose SLayer
Agent-native structure
Designed for workflows where queries are generated dynamically by AI tools rather than predefined manually.
Structured query representation makes generation more reliable than raw SQL.
Lightweight and standalone
Runs locally, embedded, or as a service
No dbt project required
No BI platform dependency
No heavy infrastructure
Fast model generation
Database schemas can be converted into semantic models automatically, including relationships between tables.
Reduces manual modeling work significantly.
Expressive query layer
Supports query-time transformations such as time_shift, diff, and dynamic aggregations.
Complex analytical queries can be expressed without complex SQL window functions.
Python-native ecosystem fit
Integrates naturally into Python-based data and agent workflows.
Works as a library, CLI tool, MCP server, or API.