ktx AI Data Agents Context Layer

Skill by ara.so — AI Agent Skills collection.

ktx is a self-improving context layer that teaches AI agents how to query data warehouses accurately using approved metric definitions, joinable columns, and business knowledge. It ingests metadata from dbt, LookML, Looker, Metabase, Notion, and raw warehouse tables, then exposes this context through CLI and MCP tools for AI agents to use.

What ktx Does

• Learns from company knowledge — ingests wiki content, organizes it, removes duplicates, flags contradictions
• Maps the data stack — samples tables, captures metadata, detects joinable columns, annotates sources
• Builds a semantic layer — combines raw tables and metrics through a join graph that resolves chasm and fan traps
• Serves agents — exposes CLI and MCP tools with semantic search across wiki and semantic-layer entities

Installation

Global Installation