ktx
ktx is an executable context layer that helps AI agents accurately query company data.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.4k
- Source
- skill-github
- Repository
- github.com/Kaelio/ktx
Overview
ktx is an executable context layer that enables Claude Code, Codex, or other AI agents to accurately query data with full company context. It automatically learns company knowledge, maps data stacks, builds a semantic layer, and provides CLI and MCP tools to agents at runtime. Ideal for scenarios where AI agents need to query warehouses using approved metric definitions.
Capabilities
- ▪Learn company knowledge and organize content
- ▪Map data stacks and detect connectable columns
- ▪Build a semantic layer to address common pitfalls
- ▪Serve agents via CLI and MCP
Use cases
Setup
npm install -g @kaelio/ktx; ktx setup; ktx status
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which databases does ktx support?
PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, SQLite.
Does ktx require additional API fees?
No, just use your own LLM API key or log in via a local proxy.
Related skills
OpenMetadata
OpenMetadata is an open data context layer that provides trustworthy data context and business semantics for AI.
XHS-Downloader
A link extraction and content collection tool for Xiaohongshu, supporting multiple download and information extraction features.
unstract
LLM-based tool for extracting structured data from unstructured documents, supporting API deployment and ETL workflows.
FinanceToolkit
Transparent and efficient financial analysis tool supporting various financial products and metrics.
deeplake
Deeplake is a data runtime designed for AI agents, offering a serverless multimodal data lake.
skills
Provides real-time market data and options analytics for AI agents.