The AI-native ClickHouse console for your cluster diagnostics, query generation, evidence-based optimization, intelligent visualization.
📖 More demo/screenshots at docs.datastoria.app
- Natural Language Data Exploration — Describe your data needs in plain English and receive optimized ClickHouse queries instantly.
- Smart Query Optimization — AI inspects schema, validates SQL, collects evidence, and recommends concrete ClickHouse performance improvements.
- Intelligent Visualization — 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 — Skill-based agent architecture that saves tokens across multi-turn conversations; apply the Official ClickHouse Agent Skills to your ClickHouse
- Multiple Model Providers — Use OpenAI, Anthropic Claude, Google Gemini, GitHub Copilot, OpenRouter, Groq, Cerebras, Nebius and more.
- GitHub Copilot Integration — Sign in with GitHub device flow and use your existing Copilot subscription for chat, query assistance, and other AI-powered workflows.
- Advanced SQL Editor — Enjoy syntax highlighting, auto-completion, and query formatting for a seamless coding experience.
- Smart Error Diagnostics — Pinpoint syntax errors instantly with precise line and column highlighting, and get AI-powered fix suggestions with one click.
- System Log Inspector — Dive deep into query execution with timeline views, topology graphs, and performance analysis as well as Materialized Views, ZooKeeper states.
- One-Click Explain — Instantly understand query execution plans with visual AST and pipeline views.
- Dependency Graph — Visualize table relationships and trace data flows through Materialized Views, Distributed tables, and external systems.
- Multi-Cluster Support — Manage multiple ClickHouse clusters effortlessly from a single interface.
- Multi-Node Dashboard — Monitor all nodes with real-time metrics, merge operations, and replication status.
- Cluster wide Dashboards — Access pre-configured panels for query performance, ZooKeeper status, and more.
- Schema Explorer — Navigate databases, tables, and columns with an intuitive tree view.
- 100% Local Execution — All SQL queries run directly from your browser to your ClickHouse server, ensuring complete privacy.
- No Data Collection — Your credentials and query results never leave your machine.
- Bring Your Own API Key — Use your own LLM API keys for AI features, keeping your data under your control.
- Browser-Side Visualization Rendering — For AI-generated visualizations, the model produces SQL and chart specs while your browser fetches and renders the data locally.
Visiting dataStoria.app to experience all features without any installation.
Prerequisites:
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 devOpen http://localhost:3000 in your browser and connect to your ClickHouse instance.
The easiest way to run DataStoria is using the pre-built Docker image:
docker run -d -p 3000:3000 frankchen021/datastoria:latestThen 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.
- Docker Deployment — Build and run with Docker
- LLM Provider API Key Configuration — Configure API keys for your LLM provider
- Authentication Guide — OAuth setup for Google, GitHub, and Microsoft
- Framework: Next.js 16 with React 19
- AI Integration: Vercel AI SDK with support for OpenAI, Anthropic, Google, Groq, and more
- Authentication: NextAuth.js
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.