mnemiq

Summary

mnemiq is an open-source text-to-SQL engine for enterprise data agents, configured to work with a user's own database. Before execution, a deterministic checker verifies that proposed SQL is read-only, uses allowed objects, compiles in the source database's dialect, and passes EXPLAIN. Permissions are applied before schema retrieval, so the model is not shown tables the caller cannot access. Each answer includes the executed SQL, tables touched, and enrichment version. The engine can profile columns and assemble descriptions, grain, glossary terms, and coded-value meanings; a human owner can certify semantic definitions. Listed database support includes PostgreSQL, SQLite, DuckDB, Oracle, Snowflake, and Databricks, with DuckDB as the universal executor. Models can use any OpenAI-compatible /v1 endpoint, including local servers such as vLLM, Ollama, llama.cpp server, and LM Studio. Its MCP server offers the read-only, access-scoped db_read(question) and get_schema() tools. One process can serve a workbench and HTTP endpoints for asking, chatting, and retrieving schema. The Apache-2.0 engine is free and runs in the user's environment. Managed grading and drift services and the control plane are separate commercial offerings.

Who it is for

mnemiq suits teams building enterprise data agents that need to query their own databases with access controls and traceable SQL. It may also suit teams that want to use a local model server within their network.

Compared on AI SQL generators

Deployment

self_hostedagenticfabriq.com

Schema context

Yesagenticfabriq.com

Facts

Purpose

mnemiq is an open-source text-to-SQL engine for enterprise data agents that can be configured and measured on a user's own database.agenticfabriq.com · 4 Oct 2026

Query checks

A deterministic decider checks that proposed SQL is read-only, uses allowed objects, compiles in the source dialect, and passes EXPLAIN before execution.agenticfabriq.com · 4 Oct 2026

Database support

The page lists PostgreSQL, SQLite, DuckDB, Oracle, Snowflake, and Databricks, with DuckDB as the universal executor.agenticfabriq.com · 4 Oct 2026

LLM support

Any OpenAI-compatible /v1 endpoint can serve the model, including local servers such as vLLM, Ollama, llama.cpp server, and LM Studio.agenticfabriq.com · 4 Oct 2026

Access control

Permissions are applied before schema retrieval, so the model is not shown tables the caller may not access.agenticfabriq.com · 4 Oct 2026

Traceability

Each answer includes the SQL that ran, the tables it touched, and the enrichment version used.agenticfabriq.com · 4 Oct 2026

Semantic enrichment

It can profile columns and build descriptions, grain, glossary terms, and coded-value meanings, with semantic definitions optionally certified by a human owner.agenticfabriq.com · 4 Oct 2026

Agent integration

The MCP server exposes two read-only, access-scoped tools: db_read(question) and get_schema().agenticfabriq.com · 4 Oct 2026

API and workbench

One process can serve a workbench and HTTP endpoints POST /v1/ask, POST /v1/chat, and GET /v1/schema.agenticfabriq.com · 4 Oct 2026

Security deployment

The maker says that using a local model server keeps every schema, question, and row inside the user's network.agenticfabriq.com · 4 Oct 2026

Commercial services

The maker identifies Verity, a managed grading and drift service, and the Agentic Fabriq control plane as commercial services around the open-source engine.agenticfabriq.com · 4 Oct 2026

Cost consideration

The launch article says mnemiq averaged around 2.3 LLM calls per question with repair enabled in its benchmark comparison, while the compared vendor APIs were called once.agenticfabriq.com · 4 Oct 2026

Company

The mnemiq page identifies Agentic Fabriq as its maintainer; the opened maker pages did not state a headquarters or founding year.agenticfabriq.com · 4 Oct 2026

Where it ranks on Everything Xiaomi

• Best AI SQL Generators in 2026#7 of 19

Sources

• agenticfabriq.com/mnemiq· checked 4 Oct 2026
• agenticfabriq.com/blog/mnemiq/launch· checked 4 Oct 2026