Docs

ClariLayer is a personal context layer for your AI coding agent, delivered over MCP. Install it once into Claude Code, Cursor, or Codex, and your agent stops re-explaining your data every session: it can recall the definitions, joins, schema notes, and gotchas you have saved, and reconcile them against your real warehouse so you know what to trust.

Start here

• Quickstart installs ClariLayer as an MCP server, mints a context key, and confirms the connection so your agent can recall your context.
• The Context Layer explains the mental model: why a personal, reconciled, in-flow context layer beats a hand-typed CLAUDE.md.
• Verified vs Asserted explains the trust-status model — what asserted, caveat, and the roadmap verified actually mean.

The four verbs

After you connect, your agent has four context tools:

• bootstrap bulk-ingests your existing SQL, dbt models, and CLAUDE.md so you do not start from an empty store.
• recall pulls the most relevant saved context for the current task, in-flow (get_analysis_context).
• remember saves a definition, schema note, join, or gotcha so your agent retains it across sessions.
• reconcile checks a saved definition against your real warehouse result; a mismatch is flagged as a caveat.

Going deeper

• AI Agent Context Guide walks through the recall-first working loop in practice.
• SaaS Metrics Definition Library is a reference for the metric definitions teams argue about most: ARR, MRR, NRR, churn, and pipeline coverage.

For teams

ClariLayer starts as your personal context layer. As teams adopt it, the personal context analysts build merges into shared, owned, governed metric context — ownership, approval, and one right definition. That team strand is kept and reachable, but secondary to the single-player wedge:

• For teams covers where ClariLayer goes as teams adopt it: personal context layers joined by a governed Context Edge — propose your definition up, adopt the team's canon down, with agency.
• API v1 overview documents the read-only Contract API an external workflow or BI tool can use to read a governed metric's canonical context.