ktx vs neocarta
Self-improving context layer for data agents — ingests dbt/Looker/wikis, maps your warehouse, builds a semantic layer with approved metrics, and serves Claude Code/Codex via CLI and MCP. — versus — Neo4j Labs' semantic layer for data agents: ingest warehouse schema, business glossary, metrics and query history into one graph, then serve it over MCP so agents route queries and write grounded SQL.
Same job — a context layer so data agents stop guessing at your warehouse. KTX ingests dbt/Looker/wikis, builds a semantic layer with approved metrics and self-improves, serving coding CLIs directly. Neocarta materializes the layer as a Neo4j graph with hybrid search and FK-aware retrieval, and is a library you assemble rather than a running service.
| ktx | neocarta | |
|---|---|---|
| Stars | 1.6k | 98 |
| Forks | 101 | 26 |
| Language | TypeScript | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 1 months ago | 4 days ago |
| Topics | rag, agents | knowledge-graphs, data |
| Curated connections | 6 | 5 |
ktx — the curator's take
Reach for it when agents re-explore your warehouse on every question and invent their own metric logic: ktx samples tables, detects joinable columns (resolving chasm/fan traps), absorbs dbt/MetricFlow/LookML/Notion knowledge into one searchable surface, and flags contradictions for human review. Read-only by design; runs locally on your own LLM keys or your Claude Code / Codex login. Skip it if you have no SQL warehouse to sit on, or for one ad-hoc query. It ingests your existing semantic layers rather than replacing them. YC-backed (Kaelio); telemetry is on by default with opt-out.
neocarta — the curator's take
The honest fix for Text2SQL: the model is not bad at SQL, it is blind to your data landscape. Neocarta pulls schema metadata, foreign keys, sample values, glossary terms, governed metric definitions and real query history into a Neo4j graph — only metadata crosses over, data stays in the source — then serves it to agents over MCP with full-text, vector and hybrid search that returns columns, types, example values and the FK references needed to build a join. Embeddings are optional; catalog search works from schema alone. It ships a runnable LangGraph + BigQuery agent so you can see the routing loop end to end. Read the label though: Neo4j Labs, explicitly experimental, not a supported product, 98 stars, and it assumes you are willing to stand up and maintain a Neo4j instance next to your warehouse.