MindsDB Query Engine
github.com
- Free plan
- Linux
- Web
- API
- Self-hosted
What MindsDB Query Engine is
MindsDB Query Engine connects data sources for live SQL queries and semantic search. The project says it supports more than 200 sources and queries them through one SQL dialect without copying data or running ETL pipelines. Named examples include PostgreSQL, MySQL, MongoDB, Snowflake, BigQuery, S3 and Slack. Users can work in an HTTP SQL editor or connect tools such as DBeaver and SQLAlchemy through MySQL and PostgreSQL wire protocols. For unstructured content, knowledge bases combine an embedding model, an optional reranking model and a vector store for indexing and retrieval. Hybrid search runs vector similarity and BM25 keyword matching together, then merges the results. Projects group work, views preserve transformations across sources, and jobs can schedule SQL to run at intervals. The engine can be run with Docker or installed from PyPI. MindsDB describes it as a way to give AI agents live, SQL-queryable access to data and semantic search. The project is free and self-hosted. MindsDB Core uses the Elastic License 2.0, while some repository directories have separate licenses.
Who it suits
MindsDB Query Engine suits teams that want to query connected data sources through SQL or add semantic search over unstructured content. It may also suit developers building AI agents that need live data access.
Good to know, and what to watch
- Queries connected sources live without copying data.
- Connects to more than 200 data sources.
- Supports MySQL and PostgreSQL wire protocols.
- Jobs can schedule SQL queries.
- Can run with Docker or install from PyPI.
- MindsDB Core uses the Elastic License 2.0.
- Some repository directories have separate licenses.
Plans
Every plan and priceOpen-source Query Engine
Open source
Getting started
- Open the MindsDB Engine GitHub repository
- Deploy the engine with Docker or install it from PyPI
- Connect databases, warehouses, applications, or files
- Use the HTTP SQL editor or connect through MySQL or PostgreSQL protocols
- Create projects, views, knowledge bases, or scheduled jobs
The verdict
MindsDB Query Engine combines federated SQL access with semantic and hybrid search. Its license terms vary across the repository, so users should check the applicable license for the components they use.
Questions people ask
What does MindsDB Query Engine cost?
It is free. The listed plan is an open-source query engine at no cost.
Is MindsDB Query Engine self-hosted?
Yes. The project documents self-hosted deployment with Docker or installation from PyPI.
Which data sources can it connect to?
The project says it connects to more than 200 sources. Examples include PostgreSQL, MySQL, MongoDB, Snowflake, BigQuery, S3, and Slack.
What license does MindsDB use?
MindsDB Core is licensed under Elastic License 2.0. The repository notes that some directories have their own licenses.
Can it run scheduled SQL?
Yes. Jobs can schedule SQL to run on an interval.
How can users get support?
The project directs questions to Discord, bugs to GitHub Issues, and commercial support inquiries to the team contact.
What the maker publishes
- Audience
- The project describes itself as a standalone open-source query engine that can give AI agents live, SQL-queryable access to data and semantic search. source
- Deployment
- The project documents running the engine with Docker or installing it from PyPI. source
- Federated queries
- It queries connected sources live through one SQL dialect without copying the data or using ETL pipelines. source
- Founded
- 2018 source
- Headquarters
- Berkeley, California, United States source
- Hybrid search
- Hybrid search runs vector similarity and BM25 keyword matching in parallel and merges the results. source
- Integrations
- The README names databases, warehouses, applications, and files as source categories and gives PostgreSQL, MySQL, MongoDB, Snowflake, BigQuery, S3, and Slack as examples. source
- Interfaces
- The engine includes an HTTP SQL editor and supports MySQL and PostgreSQL wire protocols for clients such as DBeaver and SQLAlchemy. source
- Knowledge bases
- Knowledge bases combine an embedding model, an optional reranking model, and a vector store to index and retrieve unstructured content. source
- License
- MindsDB Core is licensed under Elastic License 2.0, and the repository notes that some directories have their own licenses. source
- Maker history
- MindsDB's about page says Jorge Torres and Adam Carrigan released the first MindsDB version in Berkeley in 2018. source
- Organization and automation
- Projects namespace work, views save cross-source transformations, and jobs schedule SQL to run on an interval. source
- Purpose
- MindsDB Query Engine provides semantic search over data through SQL and connects to more than 200 data sources. source
- Security and data handling
- The README says connected source data is queried in place and is never copied, and directs vulnerability reports to its security policy instead of public issues. source
- Support
- The project points users to Discord for questions, GitHub Issues for bugs, and team contact for commercial support. source
Checked against the maker's pages on 8 Oct 2026.