kaelio.com

{"@context":"https://schema.org","@graph":[{"@type":"WebSite","@id":"https://www.kaelio.com/#website","name":"Kaelio","url":"https://www.kaelio.com","publisher":{"@id":"https://www.kaelio.com/#organization"},"speakable":{"@type":"SpeakableSpecification","cssSelector":["h1","h2","[data-speakable]"]}},{"@type":"Organization","@id":"https://www.kaelio.com/#organization","name":"Kaelio","url":"https://www.kaelio.com","logo":"https://www.kaelio.com/brand/kaelio-logo.png","description":"Kaelio auto-builds a governed context layer from your data stack so AI data agents deliver trusted, sourced answers to every team.","contactPoint":{"@type":"ContactPoint","email":"info@kaelio.com","contactType":"customer service"},"sameAs":["https://x.com/KaelioAI","https://www.linkedin.com/company/kaelio-ai/","https://www.ycombinator.com/companies/kaelio","https://docs.kaelio.com"]}]}

{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://www.kaelio.com/#software","name":"ktx","url":"https://www.kaelio.com","description":"ktx teaches agents how to query your warehouse accurately. It learns your metric definitions, joinable columns, and business knowledge, then writes them as reviewable YAML and Markdown in git. Apache 2.0. Run locally.","applicationCategory":"DeveloperApplication","operatingSystem":"macOS, Linux, Windows","featureList":["Self-improving wiki from your docs","Maps your data stack and detects joinable columns","Semantic layer with auto join resolution","Context written as YAML and Markdown in git","MCP server and CLI surface","Works with Claude Code, Claude Desktop, Codex, Cursor, OpenCode, and custom agents","Bring your own LLM keys","Apache 2.0 licensed"],"offers":[{"@type":"Offer","name":"ktx (open source)","price":"0","priceCurrency":"USD","availability":"https://schema.org/InStock","url":"https://www.kaelio.com"}],"publisher":{"@id":"https://www.kaelio.com/#organization"}}

{"@context":"https://schema.org","@type":"FAQPage","@id":"https://www.kaelio.com/#faq","url":"https://www.kaelio.com/#faq","inLanguage":"en-US","mainEntityOfPage":"https://www.kaelio.com","mainEntity":[{"@type":"Question","name":"What is ktx?","acceptedAnswer":{"@type":"Answer","text":"ktx is an open-source context layer for data agents that makes them much more accurate at querying data warehouses. It gives agents the business context, approved metric definitions, joinable columns, warehouse metadata, and query history they do not get from direct warehouse access. It also includes a query engine, so agents can query through ktx instead of writing SQL from scratch."}},{"@type":"Question","name":"Is ktx free?","acceptedAnswer":{"@type":"Answer","text":"Yes. ktx is open source under the Apache 2.0 license. There are no usage limits. You run it yourself with your own LLM API keys."}},{"@type":"Question","name":"How do I install and set up ktx?","acceptedAnswer":{"@type":"Answer","text":"Run npm install -g @kaelio/ktx, then run ktx setup from your project directory. You can also ask Claude Code, Codex, Cursor, or another coding agent to install and configure ktx for you by giving it the prompt from the ktx quickstart. Setup creates a ktx project, connects your warehouse and context sources, builds context, and can install agent integrations. ktx requires Node.js 22 or newer."}},{"@type":"Question","name":"What does ktx do that raw MCP access does not?","acceptedAnswer":{"@type":"Answer","text":"A direct warehouse MCP connector usually gives an agent access to tables, columns, and SQL execution. ktx gives the agent a query engine plus reviewable metric definitions, a mapped join graph that resolves chasm and fan traps, a wiki of business context, and the source evidence behind every definition."}},{"@type":"Question","name":"How does ktx make agent-generated SQL more reliable?","acceptedAnswer":{"@type":"Answer","text":"ktx gives agents approved context before they write or run SQL. Agents can search the wiki, find semantic-layer entities, compile governed metric queries, and run read-only SQL through configured connections. This reduces repeated schema exploration, incorrect joins, and invented metric logic."}},{"@type":"Question","name":"Does ktx send my data anywhere?","acceptedAnswer":{"@type":"Answer","text":"ktx runs locally. Your warehouse data stays in your warehouse, and local state and secrets stay in the git-ignored .ktx directory. Your LLM provider sees whatever context or query content your agent sends to it, the same as any other agent connected to your data."}},{"@type":"Question","name":"Where does ktx store context?","acceptedAnswer":{"@type":"Answer","text":"ktx stores shareable context in plain files: ktx.yaml, semantic-layer YAML, and Markdown wiki pages. Those files can be reviewed in git. Local runtime state, credentials, caches, and secrets live under .ktx and should stay out of git."}},{"@type":"Question","name":"How is ktx different from semantic layers like Cube, Malloy, or dbt MetricFlow?","acceptedAnswer":{"@type":"Answer","text":"ktx includes its own semantic layer, but it is built to be flexible and agent-native: agents can search, read, patch, and validate context through files, CLI, and MCP. Compared with standalone semantic-layer tools, ktx adds business context, source evidence, warehouse metadata, query history, and a reviewable wiki around the semantic model."}},{"@type":"Question","name":"Does ktx replace dbt, Looker, Metabase, or my BI tool?","acceptedAnswer":{"@type":"Answer","text":"No. ktx complements the tools you already use. It can ingest dbt, MetricFlow, LookML, Looker, Metabase, Notion, warehouse metadata, and query history, then expose that context to agents. Your existing transformations, dashboards, and BI workflows stay in place."}},{"@type":"Question","name":"Does ktx replace dbt?","acceptedAnswer":{"@type":"Answer","text":"No. ktx consumes dbt instead of replacing it. If you use dbt, ktx can ingest your models, metric definitions, and documentation into its context layer so agents can use that governed logic directly. If you don't use dbt, ktx can still build context from your warehouse schemas, BI tools, documentation, and query history."}},{"@type":"Question","name":"What is the difference between ktx and ktx Cloud?","acceptedAnswer":{"@type":"Answer","text":"ktx is the open-source engine. You run it yourself, locally, with your own LLM keys. ktx Cloud is the hosted version. Same engine, plus hosted runtime, multi-user workspace, review and approval workflows, SSO, continuous ingest, observability, and included LLM credits."}},{"@type":"Question","name":"Which agent clients does ktx work with?","acceptedAnswer":{"@type":"Answer","text":"ktx works with Claude Code, Claude Desktop, Codex, Cursor, OpenCode, generic .agents clients, and any custom MCP-compatible agent your team builds. ktx exposes an MCP server and a CLI, so any agent that speaks MCP can use it."}},{"@type":"Question","name":"Which warehouses and BI tools does ktx work with?","acceptedAnswer":{"@type":"Answer","text":"Warehouses: PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, SQLite, DuckDB, Amazon Athena, MongoDB, and many more. Modeling and BI: dbt, MetricFlow, LookML, Looker, Metabase, Sigma, and many more. Documentation: Notion, Google Drive, and many more."}},{"@type":"Question","name":"Can my team review and change the context ktx creates?","acceptedAnswer":{"@type":"Answer","text":"Yes. ktx is built around reviewable context files. Agents can propose updates to semantic-layer YAML or wiki Markdown, but your team can inspect, validate, and approve those changes through normal code review before they become trusted context."}},{"@type":"Question","name":"How do I contribute to ktx?","acceptedAnswer":{"@type":"Answer","text":"ktx is open source. Issues, pull requests, and discussions are welcome on the GitHub repository."}}]}