nlqdb — analytical memory for AI agents

Name: nlqdb — analytical memory for AI agents
Author: nlqdb

Analytical memory for AI agents: a real Postgres your agent connects to over MCP and queries in plain English — GROUP BY, JOIN, aggregate over what it…

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

Nlqdb Query: Query your agent's structured memory in natural language — a real database it can GROUP BY / JOIN / aggregate over, not just recall. Returns rows + the compiled SQL (in trace). The databa
Nlqdb List Databases: List the memory databases your agent can query, scoped to the authenticated user. Requires a user-scoped key (sk_live_ or sk_mcp_). Returns engine per row.
Nlqdb Describe: Inspect the shape of one of your agent's memory databases. Return schema metadata (slug, engine, schema name) for one database. Requires a user-scoped key (sk_live_ or sk_mcp_).

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Analytical memory for AI agents: a real Postgres your agent connects to over MCP and queries in plain English — GROUP BY, JOIN, aggregate over what it remembered, not just the top-k a vector store recalls. One command to connect.

Список инструментов сервера (5)

Технические названия из tools/list. Нужны только разработчикам.

nlqdb_query	Query your agent's structured memory in natural language — a real database it can GROUP BY / JOIN / aggregate over, not just recall. Returns rows + the compiled SQL (in trace). The database is materialised on first reference — no separate create tool. Destructive plans return requires_confirm: true + a diff; re-call with confirm: true to commit.
nlqdb_list_databases	List the memory databases your agent can query, scoped to the authenticated user. Requires a user-scoped key (sk_live_ or sk_mcp_). Returns engine per row.
nlqdb_describe	Inspect the shape of one of your agent's memory databases. Return schema metadata (slug, engine, schema name) for one database. Requires a user-scoped key (sk_live_ or sk_mcp_).
nlqdb_remember	Write a typed row into your agent's memory database — a fact to recall later, a conversation episode, or an entity (person/project/thing). Materialises directly into the agent_memory_v1 schema with no LLM in the loop, so it's deterministic. The DB must be an agent_memory_v1 preset; query it back later with nlqdb_query (which can GROUP BY / aggregate over what you remembered).
nlqdb_connect_database	Connect an existing ClickHouse or Postgres database so the agent can query it in natural language with nlqdb_query — no migration, no schema upload. Pass the engine and a connection URL; the credential is stored sealed server-side and never echoed back. Returns the new dbId and a preview of the discovered schema.