agami-core

Local, governed semantic layer that gives AI coding agents correct SQL and an audit receipt on every answer.

Pluginfree

agami-core is an open-source trust layer that sits between AI coding agents and a database, building a governed semantic model from the live schema. It enforces correct joins and approved metric definitions, and returns a full audit trail with every answer so users can verify how a number was produced. It's aimed at developers and data teams who use AI agents like Claude Code to query enterprise databases and need answers they can trust and check.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of agami-core - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim agami-core to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether agami-core (or something else) actually fits.

Try a problem