SLayer
Text to SQL fails quietly. The model guesses a join, invents a revenue definition, and returns a number that looks right. SLayer, from MotleyAI, stops that guesswork by holding one definition of each metric and letting agents query it instead of writing SQL. Define revenue once, then ask for sum of revenue, average revenue, or revenue shifted a year back, and SLayer compiles the correct query for your database. Agents reach it over MCP, REST, CLI, Python, Flight SQL, or a Postgres facade, and it can import dbt, Cube, and Ossie configs. Version 1.8.2 shipped on 9 November 2026, and the repo now has 341 stars under the MIT license.
What you get
- One definition of each metric, so revenue means the same thing in every agent query
- Six ways in for agents: MCP, REST, CLI, Python, Flight SQL, or a Postgres facade
- Imports from dbt, Cube, and Ossie, so the models you already have carry over
- A small, focused project: v1.8.2, 341 stars, MIT licensed, written in Python
Define the metric once. Every agent answer after that is built on the same definition.
Repo: https://github.com/MotleyAI/slayer
Quick poll
What would you use SLayer for first?
- Defining metrics once for my agents
- Replacing hand-written SQL in agents
- Importing dbt or Cube configs
- Watching it for now
Vote in the comments.
If you found SLayer interesting, I write about tools like this every week in The AI-Native Engineering Leader, what actually works for engineering leaders building with AI agents, and what to skip.
Top comments (0)