Sandbox
@FrankChen021/datastoria

ClickHouse AI console for queries and cluster diagnostics

DataStoria is a ClickHouse console that helps you generate SQL, inspect query behavior, and visualize results from plain language. It connects to your ClickHouse instance, supports multiple model providers, and keeps query execution local in the browser.

327 starsโ€ข18 forksโ€ขTypeScriptโ€ขUpdated 1mo ago
Who it's for

Builders who use ClickHouse and want a console for query help, cluster monitoring, and data visualization.

What it delivers

You can ask for queries, inspect cluster health, and build charts from one ClickHouse interface instead of switching tools.

What it does

Natural language data exploration

You can describe what you need in plain English and get ClickHouse SQL back.

Smart query optimization

It inspects schema and SQL, gathers evidence, and suggests concrete ClickHouse performance improvements.

Intelligent visualization

You can ask for a chart and get both the SQL and the visualization spec for common chart types.

Advanced SQL editor

It provides syntax highlighting, auto-completion, and formatting for writing and refining queries.

System log inspector

You can review query execution timelines, topology graphs, performance details, Materialized Views, and ZooKeeper state.

Cluster dashboards

It shows multi-cluster and multi-node views for metrics, merge operations, replication status, and query performance.

Browser-side execution

SQL runs directly from your browser to ClickHouse so credentials and results stay local.

How to get it

  1. 1The easiest way to run DataStoria is using the pre-built Docker image
    docker run -d -p 3000:3000 frankchen021/datastoria:latest

README

DataStoria

The AI-native ClickHouse console for your cluster diagnostics, query generation, evidence-based optimization, intelligent visualization.

Demo

โ–ถ Watch demo

๐Ÿ“– More demo/screenshots at docs.datastoria.app


๐Ÿš€ Key Features

๐Ÿค– AI Features

  • Natural Language Data Exploration โ€” Describe your data needs in plain English and receive optimized ClickHouse queries instantly.
  • Smart Query Optimization โ€” AI inspects schema, validates SQL, collects evidence, and recommends concrete ClickHouse performance improvements.
  • Intelligent Visualization โ€” Ask for a chart in plain language and DataStoria generates both the SQL and the visualization spec for time series, bar, pie, and table views.
  • Agent SKILLs Supported โ€” Skill-based agent architecture that saves tokens across multi-turn conversations; apply the Official ClickHouse Agent Skills to your ClickHouse
  • Multiple Model Providers โ€” Use OpenAI, Anthropic Claude, Google Gemini, GitHub Copilot, OpenRouter, Groq, Cerebras, Nebius and more.
  • GitHub Copilot Integration โ€” Sign in with GitHub device flow and use your existing Copilot subscription for chat, query assistance, and other AI-powered workflows.

โšก Powerful Query Experience

  • Advanced SQL Editor โ€” Enjoy syntax highlighting, auto-completion, and query formatting for a seamless coding experience.
  • Smart Error Diagnostics โ€” Pinpoint syntax errors instantly with precise line and column highlighting, and get AI-powered fix suggestions with one click.
  • System Log Inspector โ€” Dive deep into query execution with timeline views, topology graphs, and performance analysis as well as Materialized Views, ZooKeeper states.
  • One-Click Explain โ€” Instantly understand query execution plans with visual AST and pipeline views.
  • Dependency Graph โ€” Visualize table relationships and trace data flows through Materialized Views, Distributed tables, and external systems.

๐Ÿ“Š Cluster Monitoring & Management

  • Multi-Cluster Support โ€” Manage multiple ClickHouse clusters effortlessly from a single interface.
  • Multi-Node Dashboard โ€” Monitor all nodes with real-time metrics, merge operations, and replication status.
  • Cluster wide Dashboards โ€” Access pre-configured panels for query performance, ZooKeeper status, and more.
  • Schema Explorer โ€” Navigate databases, tables, and columns with an intuitive tree view.

๐Ÿ”’ Privacy & Security

  • 100% Local Execution โ€” All SQL queries run directly from your browser to your ClickHouse server, ensuring complete privacy.
  • No Data Collection โ€” Your credentials and query results never leave your machine.
  • Bring Your Own API Key โ€” Use your own LLM API keys for AI features, keeping your data under your control.
  • Browser-Side Visualization Rendering โ€” For AI-generated visualizations, the model produces SQL and chart specs while your browser fetches and renders the data locally.

๐ŸŒ Experience the app

Visiting dataStoria.app to experience all features without any installation.


๐Ÿ› ๏ธ Build from Source

Prerequisites:

  • Node.js v22 or later
  • pnpm (install via npm install -g pnpm)

Follow these steps to build and run locally:

# Clone the repository
git clone --recurse-submodules https://github.com/FrankChen021/datastoria.git
cd datastoria

# Install dependencies
npm install --force

# Start the development server
npm run dev

Open http://localhost:3000 in your browser and connect to your ClickHouse instance.


๐Ÿณ Running with Docker

The easiest way to run DataStoria is using the pre-built Docker image:

docker run -d -p 3000:3000 frankchen021/datastoria:latest

Then open http://localhost:3000 in your browser.

The Docker image supports both linux/amd64 and linux/arm64 platforms, so it runs natively on Intel/AMD machines as well as Apple Silicon Macs and ARM-based servers.


๐Ÿ“– Documentation

User Manual

Development


๐Ÿงฐ Tech Stack


๐Ÿ“œ License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.


DataStoria is an AI-native ClickHouse console for modern query, visualization, and diagnostics workflows.

Files in the repo

Repository payloadโ€ข32 top-level entries
  • .codex
  • .github
  • docker
  • docs
  • external
  • public
  • resources
  • scripts
  • src
  • .dockerignore
  • .env.example
  • .eslintrc.json
  • .gitignore
  • .gitmodules
  • .npmrc
  • .prettierignore
  • .prettierrc
  • AGENTS.md
  • components.json
  • eslint.config.mjs
  • instrumentation.ts
  • LICENSE
  • next.config.ts
  • package-lock.json
  • package.json
  • postcss.config.mjs
  • README.md
  • tailwind.config.mjs
  • tsconfig.json
  • tsconfig.typecheck.json
  • vercel.json
  • vitest.config.ts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More tools

JuliusBrussee/
caveman

๐Ÿชจ why use many token when few token do trick โ€” Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
MemPalace/
mempalace

The best-benchmarked open-source AI memory system. And it's free.

59k
stablyai/
orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

66k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

132k

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

64k
headroomlabs-ai/
headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

71k