- Home
- AI SQL Generators
- mnemiq
mnemiq
What it is
mnemiq is an open-source text-to-SQL engine for enterprise data agents, configured and measured against your own database. Before a query runs, its deterministic decider checks that SQL is read-only, refers only to allowed 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 executed, the tables touched and the enrichment version used. The engine can profile columns and develop descriptions, grain, glossary terms and meanings for coded values; a human owner can certify semantic definitions. Listed databases include 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, and one process can serve a workbench plus HTTP endpoints. The Apache-2.0 engine is free and runs in your environment; managed services around it are separate commercial offerings.
For and against
For
- Checks proposed SQL before execution.
- Applies permissions before schema retrieval.
- Answers include SQL, touched tables and enrichment version.
- Supports six listed database systems.
- Free Apache-2.0 engine runs in your environment.
Against
- Managed grading and control-plane services are separate commercial offerings.
- Benchmark comparison reports around 2.3 LLM calls per question with repair enabled.
The verdict
mnemiq combines guarded SQL execution with access controls and answer traceability. Teams should account for the separate commercial services if they need managed grading or the control plane.
Who it suits
mnemiq suits teams building enterprise data agents that need SQL access scoped to their own database. It is also a fit for teams that want local model-server options and traceable query results.
Plans and prices
mnemiq
Open-source Apache-2.0 engine · runs in your own environment
Read 4 Oct 2026 · agenticfabriq.com
Verity and Agentic Fabriq control plane
Managed grading and drift service · identity, vaulted credentials, per-group grants and audit across sources
Read 4 Oct 2026 · agenticfabriq.com
On the record
- Access control
- Permissions are applied before schema retrieval, so the model is not shown tables the caller may not access.agenticfabriq.com · read 4 Oct 2026
- Agent integration
- The MCP server exposes two read-only, access-scoped tools: db_read(question) and get_schema().agenticfabriq.com · read 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 · read 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 · read 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 · read 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 · read 4 Oct 2026
- Database support
- The page lists PostgreSQL, SQLite, DuckDB, Oracle, Snowflake, and Databricks, with DuckDB as the universal executor.agenticfabriq.com · read 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 · read 4 Oct 2026
- 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 · read 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 · read 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 · read 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 · read 4 Oct 2026
- Traceability
- Each answer includes the SQL that ran, the tables it touched, and the enrichment version used.agenticfabriq.com · read 4 Oct 2026
