DeepInsight-AI/DeepBI

LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.

What it solves

DeepBI is an AI-native data analysis platform designed to help users explore, query, and visualize data from various sources without needing to write complex queries manually. It enables data-driven decision-making through a conversational interface.

How it works

DeepBI uses large language models (LLMs) to translate user dialogues into data results and persistent queries. It connects to multiple data sources—including SQL databases and flat files—to retrieve information and generate visualizations that can be organized into dashboards.

Who it’s for

It is designed for users who want to perform data analysis and gain insights from their databases or spreadsheets using natural language instead of traditional BI tools or manual coding.

Highlights

  • Conversational Analysis: Get data results and analysis through direct dialogue.
  • Conversational Query Generation: Create persistent queries and visualizations via chat.
  • Dashboarding: Assemble saved visualizations into custom dashboards.
  • Broad Data Support: Compatible with MySQL, PostgreSQL, Doris, StarRocks, MongoDB, and CSV/Excel files.
  • Cross-Platform: Supports Windows, Linux, and Mac.

Related

  • Project
    vercel/chat

    A unified TypeScript SDK for building chat bots once and deploying them across multiple platforms like Slack, Discord, and WhatsApp, featuring native AI streaming support.

  • Project
    heshengtao/comfyui_LLM_party

    A comprehensive set of ComfyUI nodes for building LLM workflows, enabling the integration of AI agents, RAG, and VLMs into visual image generation pipelines.

  • Project
    tavily-ai/tavily-mcp

    Tavily MCP is a Model Context Protocol server that exposes four web‑knowledge tools—search, extract, map, and crawl—so LLM‑based agents (Claude Code, Cursor, etc.) can fetch up‑to‑date web data, pull page content, generate site maps, or bulk‑crawl sites. It can be used via Tavily’s hosted endpoint or run locally with a single `npx` command, authenticating with an API key or optional OAuth. Configuration is done through environment variables (`TAVILY_API_KEY`, `DEFAULT_PARAMETERS`, `TAVILY_HUMAN_ID`). The server enables real‑time web access for AI assistants, RAG pipelines, and productivity tools without custom scraping code.

  • Project
    FrancyJGLisboa/agent-skills-platform

    A platform that converts real-world business workflows into tested, installable agent skills that can be safely published and governed within a team marketplace.