Questions, not dashboards
Ask how many orders shipped late last week; Memtro reads the schema, writes the SQL, runs it read-only and shows the query.
Read-only SQL over your warehouse or application database, written by the model from the schema.
Give Memtro a read-only role and the model can read the schema and run SELECT queries. In agent mode it looks at the schema first, then queries by the identifiers it found in a ticket or a CRM record.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Postgres tool, reads what it needs, and answers with the source cited.
Ask how many orders shipped late last week; Memtro reads the schema, writes the SQL, runs it read-only and shows the query.
Every statement runs in a READ ONLY transaction with a timeout and a row cap, through an SSH tunnel if the database is private.
Questions people ask once Postgres is connected. In agent mode each one also checks the other systems that know about the same people, companies or identifiers.
Teams that get the most from Postgres in Memtro, with the rest of their stack attached.
A record in Postgres is rarely the whole story. Connect the systems that hold the rest and the agent cross-references them by default, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Postgres tools are the same everywhere.
Clients and agents →Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.