Ross ROSS = Recommend OSS · open-source software intelligence for agents

Kaelio/ktx

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company observed · 2026-08-28

github.com/Kaelio/ktx · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

75/100

  • Activity 93
  • Release rhythm 91
  • Longevity 8

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 2.0
  • age_days: 115
  • days_rel: 61
  • days_push: 45
  • n_releases_24m: 19

Full methodology

Adoption not part of the score

1562 stars · 100 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ktx is an open-source, self-improving context layer for data and analytics agents, distributed as an npm CLI. It ingests warehouse metadata, BI tool definitions, query history, and docs into reviewable YAML/Markdown files, then serves that context to AI agents via CLI and MCP tools for semantic querying and read-only SQL execution.

Use cases

  • let Claude Code or Codex query my data warehouse accurately with business context
  • give AI agents approved metric definitions and safe joins before they write SQL
  • build a semantic layer as code that agents can search and execute
  • stop agents from writing plausible but wrong analytics SQL
  • federate read-only SQL queries across postgres, mysql, sqlite, and duckdb
  • maintain a wiki of business knowledge that agents can retrieve at query time
  • review agent-generated analytics context as git diffs

When to choose

  • your team uses AI coding agents to answer data questions against a warehouse
  • you want metric definitions, joins, and business rules version-controlled and reviewable
  • you need cross-database federation without ETL
  • you want an MCP server exposing semantic queries and read-only SQL to agents

When to avoid

  • you need a hosted BI dashboard for non-technical users
  • your stack relies only on warehouses not supported by the federation engine (e.g., Snowflake, BigQuery) for cross-database joins
  • you want a fully managed semantic layer with a web UI rather than files on disk

Facets

cli-tool · maturity active

mcp rag search-engine cli developer-tools data-science analytics artificial-intelligence databases cli cross-platform semantic-layer context-layer data-agents analytics-engineering claude-code mcp-server duckdb context-as-code business-intelligence data-engineering ai-agents nodejs

10 sources

Member repositories

RepositoryRoleHealth v2
Kaelio/ktxmain75

For agents

markdown · JSON · MCP: product_card(name="Kaelio/ktx")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem