mindsdb

    mindsdb/mindshub

    #298 this week

    Make AI do actual work. Swap the model anytime — keep everything you've built.

    ai
    analytics
    database
    llm
    agents
    anton
    artificial-inteligence
    claude
    claude-cowork
    Makefile
    MIT
    39.5K stars
    6.2K forks
    39.5K GitHub watchers
    Updated 8/5/2026
    View on GitHub

    Backblaze Generative Media Hackathon

    Build the next generation of AI media apps with Genblaze, stored on Backblaze B2. $10,000 in prizes.

    Enter the hackathon

    Loading star history...

    Use Cases & Benefits

    • Enables AI agents and applications to securely query and analyze data from multiple heterogeneous data sources using a unified query engine.
    • Provides seamless connection, unification, and querying of large-scale federated data without requiring complex ETL processes.
    • Use for building AI-powered analytics platforms that integrate data from diverse databases and SaaS applications in real time.
    • Use for creating conversational AI agents that answer complex business intelligence questions by querying unified data views.
    • Use for automating data synchronization and transformation jobs to maintain up-to-date, indexed knowledge bases for efficient Q&A.

    About mindshub


    MindsDB enables humans, AI, agents, and applications to get highly accurate answers across large scale data sources.

    MindsDB Demo

    Install MindsDB Server

    MindsDB is an open-source server that can be deployed anywhere - from your laptop to the cloud, and everywhere in between. And yes, you can customize it to your heart's content.

    • Using Docker Desktop. This is the fastest and recommended way to get started and have it all running.
    • Using Docker. This is also simple, but gives you more flexibility on how to further customize your server.

    MindsDB has an MCP server built in that enables your MCP applications to connect, unify and respond to questions over large-scale federated data—spanning databases, data warehouses, and SaaS applications.


    Core Philosophy: Connect, Unify, Respond

    MindsDB's architecture is built around three fundamental capabilities:

    Connect Your Data

    You can connect to hundreds of enterprise data sources (learn more). These integrations allow MindsDB to access data wherever it resides, forming the foundation for all other capabilities.

    Unify Your Data

    In many situations, it’s important to be able to prepare and unify data before generating responses from it. MindsDB SQL offers knowledge bases and views that allow indexing and organizing structured and unstructured data as if it were unified in a single system.

    • KNOWLEDGE BASES – Index and organize unstructured data for efficient Q&A.
    • VIEWS – Simplify data access by creating unified views across different sources (no-ETL).

    Unification of data can be automated using JOBs

    • JOBS – Schedule synchronization and transformation tasks for real-time processing.

    Respond From Your Data

    Chat with Your Data

    • AGENTS – Configure built-in agents specialized in answering questions over your connected and unified data.
    • MCP – Connect to MindsDB through the MCP (Model Context Protocol) for seamless interaction.

    🤝 Contribute

    Interested in contributing to MindsDB? Follow our installation guide for development.

    You can find our contribution guide here.

    We welcome suggestions! Feel free to open new issues with your ideas, and we’ll guide you.

    This project adheres to a Contributor Code of Conduct. By participating, you agree to follow its terms.

    Also, check out our community rewards and programs.

    🤍 Support

    If you find a bug, please submit an issue on GitHub.

    Here’s how you can get community support:

    For commercial support, please contact the MindsDB team.

    💚 Current Contributors

    Generated with contributors-img.

    🔔 Subscribe for Updates

    Join our Slack community

    Discover Repositories

    Search across tracked repositories by name or description