mnemiq

6.9easy start · #7 of 19
in AI SQL Generators

Free to practise onyes
Free trialnot on record
Well documentedyes
Runs where you worknot on record

Runs on api, self-hosted, Web.

mnemiq is ranked #7 of 19 in AI SQL generators on The Geeks Club. It runs on API, Self-hosted, Web. There is a free plan.

mnemiq plans and pricing

All plans

mnemiq Free Open-source Apache-2.0 engine · runs in your own environment agenticfabriq.com · 4 Oct 2026

Verity and Agentic Fabriq control plane Not published Pricing page lists custom Enterprise pricing for Fabriq; it does not state a mnemiq-specific price. Managed grading and drift service · identity, vaulted credentials, per-group grants and audit across sources agenticfabriq.com · 4 Oct 2026

Compared on AI SQL generators

Deployment: self_hosted
Schema context: Yes

Best mnemiq alternatives

See all 12

QueryPlane 0 of 4 in the starter kit Lesson 17.6 Wren AI 0 of 4 in the starter kit Lesson 27.6 Outerbase AI 0 of 4 in the starter kit Lesson 37.3 Text2SQL.ai 0 of 4 in the starter kit Lesson 47.2 SQL Mocker 0 of 4 in the starter kit Lesson 57.1 NatureQuery 0 of 4 in the starter kit Lesson 67.0

The record

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.
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.
Database support: The page lists PostgreSQL, SQLite, DuckDB, Oracle, Snowflake, and Databricks, with DuckDB as the universal executor.
LLM support: Any OpenAI-compatible /v1 endpoint can serve the model, including local servers such as vLLM, Ollama, llama.cpp server, and LM Studio.
Access control: Permissions are applied before schema retrieval, so the model is not shown tables the caller may not access.
Traceability: Each answer includes the SQL that ran, the tables it touched, and the enrichment version used.
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.
Agent integration: The MCP server exposes two read-only, access-scoped tools: db_read(question) and get_schema().
API and workbench: One process can serve a workbench and HTTP endpoints POST /v1/ask, POST /v1/chat, and GET /v1/schema.
Security deployment: The maker says that using a local model server keeps every schema, question, and row inside the user's network.
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.
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.
Company: The mnemiq page identifies Agentic Fabriq as its maintainer; the opened maker pages did not state a headquarters or founding year.
Price from: Free

Where it ranks on The Geeks Club

Best AI SQL Generators in 2026#7 of 19

Is mnemiq yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote mnemiq

Sources

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