description: Connect KTX to warehouses, analytics tools, and coding agents.
---
KTX integrations bring trusted context into an analytics project and make that
context available to coding agents through the CLI. Start with `ktx setup` when
you want the guided flow, then use the integration reference pages for exact
configuration fields, generated files, and manual setup.
## Integration types
| Type | What it connects | Start here |
|------|------------------|------------|
| Primary sources | Warehouses and databases that KTX scans for schemas, constraints, row counts, and optional query history | [Primary Sources](/docs/integrations/primary-sources) |
| Context sources | Existing analytics and knowledge tools such as dbt, MetricFlow, LookML, Metabase, Looker, and Notion | [Context Sources](/docs/integrations/context-sources) |
| Agent clients | Claude Code, Codex, Cursor, OpenCode, and universal `.agents` consumers | [Agent Clients](/docs/integrations/agent-clients) |
## Recommended setup flow
Use this order for a new project:
1. Run `ktx setup` from the analytics project directory.
2. Configure an LLM backend and embeddings so KTX can enrich and search context.
3. Add at least one primary source connection.
4. Add optional context sources that describe the same warehouse or business domain.
5. Build context during setup, or run `ktx ingest <connectionId>` later.
6. Install agent integration with `ktx setup --agents` when the context is ready.
For repeatable setup, pass `--project-dir`, `--no-input`, and the relevant
automation flags documented in [`ktx setup`](/docs/cli-reference/ktx-setup).