StackMap
Subscribe

ktx vs scout

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 — Company intelligence agent that navigates Slack, Drive, wiki and CRM live — no ingest/embed pipeline — and builds its own wiki + CRM as it learns your company.

The curated verdict

Two ways to hand agents company context: ktx curates a semantic layer over your warehouse with approved metrics; Scout navigates Slack/Drive/wiki/CRM live and writes its own wiki+CRM as it learns.

ktxscout
Stars1.5k634
Forks9358
LanguageTypeScriptPython
LicenseApache-2.0Apache-2.0
Last activity5 days ago7 days ago
Topicsrag, agentsagents, memory
Curated connections21

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.

scout — the curator's take

The navigation-over-search thesis applied to company knowledge: ls/grep/follow-the-link across live sources instead of chunk-embed-pray. Built on Agno's AgentOS. Pick it to prototype a 'company brain' on live sources; skip if you need strict access-control auditing or a classic ingested RAG corpus.