iunera/philter repository overview

⁠Data Philter

Sovereign AI for Natural Language to SQL (NL2SQL) analytics.

Data Philter Core is the backend for Data Philter⁠, a local-first, privacy-focused conversational interface for enterprise data. Designed and developed by the experts at iunera⁠, this sovereign AI gateway translates Natural Language to SQL (NL2SQL), allowing users to query databases like Apache Druid⁠ and ClickHouse⁠ using plain English.

Running completely locally, Data Philter operates entirely within your infrastructure, leveraging Local LLM technology and the Model Context Protocol (MCP) to ensure data privacy and security. It empowers data scientists, site reliability engineers, and data engineers to analyze data without it ever leaving their environment. By default, connections to databases are established in "readonly mode," ensuring data safety. For Apache Druid, this is facilitated via the Apache Druid MCP Server⁠.

Stop writing arduous queries and start unlocking insights with ease through secure, conversational AI.

Please note: Data Philter is currently in an early development stage. While functional, it is actively being improved, and features may evolve rapidly. We welcome feedback and contributions!

⁠Key Features

• Sovereign AI & Privacy-Focused: Runs completely locally (Local LLM) to keep your enterprise data secure and within your infrastructure.
• Natural Language to SQL (NL2SQL): Ask questions in plain English and get results from your database automatically.
• Powered by Model Context Protocol (MCP): Utilizes the robust and extensible MCP⁠ for AI-driven data interaction.
• Multi-Database Support: Supports Apache Druid and ClickHouse⁠ for time-series analysis and more.
• Easy Setup: Get up and running quickly with our Docker and Kubernetes friendly setup.
• Flexible AI Model Support: Supports local Ollama models (e.g., iunera/aura-m, iunera/aura-l, iunera/aura-xl) and OpenAI.
  • iunera/aura-m: https://ollama.com/iunera/aura-m⁠
  • iunera/aura-l: https://ollama.com/iunera/aura-l⁠
  • iunera/aura-xl: https://ollama.com/iunera/aura-xl⁠
• Safe by Default: Establishes a "readonly" connection to prevent accidental data changes.

⁠About iunera

This project is developed and maintained by iunera⁠, a leading provider of advanced AI and data analytics solutions.

⁠Need Expert Apache Druid Consulting?

Maximize your return on data with professional Druid implementation and optimization services. From architecture design to performance tuning and AI integration, our experts help you navigate Druid's complexity and unlock its full potential.

Get Expert Druid Consulting →⁠

⁠Need Enterprise MCP Server / AI or LLM Development Consulting?

ENTERPRISE AI INTEGRATION & CUSTOM MCP (MODEL CONTEXT PROTOCOL) SERVER DEVELOPMENT

Iunera specializes in developing production-grade AI agents and enterprise-grade LLM solutions, helping businesses move beyond generic AI chatbots. They build secure, scalable, and future-ready AI infrastructure, underpinned by the Model Context Protocol (MCP), to connect proprietary data, legacy systems, and external APIs to advanced AI models.

Get Enterprise MCP Server Development Consulting →⁠

For more information about our services and solutions, visit www.iunera.com⁠.

⁠Contact & Support

Need help? Let us know!

• Website: https://www.iunera.com⁠
• GitHub Repository: https://github.com/iunera/data-philter⁠
• Professional Services: Contact us through email⁠ for Apache Druid enterprise consulting, support and custom development⁠
• Open Source: This project is open source and community contributions are welcome

---

© 2025 iunera⁠. Licensed under the Apache License 2.0.