Skip to content
SPECIFICTION
Get listed

mnemiq

agenticfabriq.com

Free plan WebAPISelf-hosted
Visit agenticfabriq.com
Spec score 7.8 #8 of 19 in AI SQL Generators

What it is

mnemiq is an open-source text-to-SQL engine for enterprise data agents, configured and measured against a user's own database. Before execution, a deterministic check verifies that proposed SQL is read-only, uses permitted objects, compiles in the source dialect, and passes EXPLAIN. Access permissions apply before schema retrieval, so the model is not shown tables the caller cannot access. Each answer includes the SQL run, the tables it touched, and the enrichment version used. mnemiq can profile columns and build descriptions, grain, glossary terms, and coded-value meanings; a human owner can certify semantic definitions. Listed databases are 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 two read-only, access-scoped tools: db_read(question) and get_schema(). One process can also 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. Local model hosting keeps schemas, questions, and rows inside the user's network, according to the maker.

Spec sheet

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.Read 4 Oct 2026 · agenticfabriq.com
Company
The mnemiq page identifies Agentic Fabriq as its maintainer; the opened maker pages did not state a headquarters or founding year.Read 4 Oct 2026 · agenticfabriq.com
Access control
Permissions are applied before schema retrieval, so the model is not shown tables the caller may not access.Read 4 Oct 2026 · agenticfabriq.com
Agent integration
The MCP server exposes two read-only, access-scoped tools: db_read(question) and get_schema().Read 4 Oct 2026 · agenticfabriq.com
API and workbench
One process can serve a workbench and HTTP endpoints POST /v1/ask, POST /v1/chat, and GET /v1/schema.Read 4 Oct 2026 · agenticfabriq.com
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.Read 4 Oct 2026 · agenticfabriq.com
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.Read 4 Oct 2026 · agenticfabriq.com
Database support
The page lists PostgreSQL, SQLite, DuckDB, Oracle, Snowflake, and Databricks, with DuckDB as the universal executor.Read 4 Oct 2026 · agenticfabriq.com
LLM support
Any OpenAI-compatible /v1 endpoint can serve the model, including local servers such as vLLM, Ollama, llama.cpp server, and LM Studio.Read 4 Oct 2026 · agenticfabriq.com
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.Read 4 Oct 2026 · agenticfabriq.com
Security deployment
The maker says that using a local model server keeps every schema, question, and row inside the user's network.Read 4 Oct 2026 · agenticfabriq.com
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.Read 4 Oct 2026 · agenticfabriq.com
Traceability
Each answer includes the SQL that ran, the tables it touched, and the enrichment version used.Read 4 Oct 2026 · agenticfabriq.com

Plans and prices

mnemiq Free Open-source Apache-2.0 engine · runs in your own environment Read 4 Oct 2026 · agenticfabriq.com
Verity and Agentic Fabriq control plane Priced on request 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 Read 4 Oct 2026 · agenticfabriq.com

Every mnemiq plan and price →

Strong points and limits

Strong points

  • Checks SQL before execution
  • Applies permissions before schema retrieval
  • Answers include SQL, touched tables, and enrichment version
  • Free Apache-2.0 engine runs in your environment

Limits

  • Managed services have no mnemiq-specific price listed
  • Benchmark comparison averaged around 2.3 LLM calls per question with repair enabled

Who it suits

mnemiq suits teams building enterprise data agents that need text-to-SQL configured on their own database, with access controls and query traceability. It is aimed at users able to run the engine in their own environment and configure a compatible model endpoint.

Verdict

mnemiq specifies its query checks, access controls, database support, and answer traceability. Its engine is free, while managed services are separate commercial offerings with no mnemiq-specific price listed.

Where Specifiction places it

Alternatives to mnemiqAll alternatives →