https://github.com/dorylab/dory
AI-native SQL workspace for modern databases. SQL Copilot, schema-aware editor, database chat, and operational tools in one place.
https://github.com/dorylab/dory
ai ai-copilot clickhouse data-studio database database-client database-tools developer-tools mysql nextjs query-editor sql sql-client sql-editor
Last synced: 19 days ago
JSON representation
AI-native SQL workspace for modern databases. SQL Copilot, schema-aware editor, database chat, and operational tools in one place.
- Host: GitHub
- URL: https://github.com/dorylab/dory
- Owner: dorylab
- License: apache-2.0
- Created: 2026-01-10T10:11:46.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-02-27T17:20:17.000Z (about 1 month ago)
- Last Synced: 2026-02-27T21:41:49.719Z (about 1 month ago)
- Topics: ai, ai-copilot, clickhouse, data-studio, database, database-client, database-tools, developer-tools, mysql, nextjs, query-editor, sql, sql-client, sql-editor
- Language: TypeScript
- Homepage: https://github.com/dorylab/dory
- Size: 7.49 MB
- Stars: 14
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Security: SECURITY.md
Awesome Lists containing this project
README
# Dory
**Dory is an AI-native SQL Studio for modern databases.**
> The AI-powered Data Studio you’ve been waiting for.
It combines intelligent SQL editing, context-aware AI assistance, conversational database exploration, and deep operational integration across modern databases into a single unified studio — helping engineers and analysts write, understand, and manage data more efficiently.
🚀 Try Live Demo •
📦 Quick Start •
⭐ Star
**No signup required. Click “Enter as Demo” to start instantly.**
**👇 Live Playground: https://demo.getdory.dev**
## 🚀 Quick Start
### Run with Docker
Make sure Docker is installed, then run:
```bash
docker run -d --name dory \
-p 3000:3000 \
-e TRUSTED_ORIGINS="http://localhost:3000" \
-e DS_SECRET_KEY="$(openssl rand -base64 32 | tr -d '\n')" \
-e BETTER_AUTH_SECRET="$(openssl rand -hex 32)" \
-e DORY_AI_PROVIDER=openai \
-e DORY_AI_MODEL=gpt-4o-mini \
-e DORY_AI_API_KEY=your_api_key_here \
-e DORY_AI_URL=https://api.openai.com/v1 \
dorylab/dory:latest
```
### 🧠 Supported AI Providers
Dory is built with a pluggable AI provider architecture.
You can freely switch between different model vendors by changing environment variables — no code changes required.
Currently supported providers:
| Provider | Env `DORY_AI_PROVIDER` | Description |
|----------|-------------------------|-------------|
| OpenAI | `openai` | Default provider. Uses official OpenAI API. |
| OpenAI-Compatible | `openai-compatible` | Any service exposing an OpenAI-compatible API. |
| Anthropic | `anthropic` | Claude models via Anthropic official API. |
| Google | `google` | Gemini models via Google Generative AI API. |
| Qwen (Alibaba) | `qwen` | Qwen models via DashScope OpenAI-compatible endpoint. |
| xAI | `xai` | Grok models via xAI API. |
## ✨ Key Features
### 🧠 SQL Copilot
An AI assistant grounded in real database schema and current query context.
- **Ask** — Generate SQL from natural language
- **Action** — Fix or rewrite the current SQL
- **Context** — Explain query logic and field semantics
AI that understands your database — not just text completion.
---
### ⌨️ Schema-Aware Autocomplete
- SQL completion based on real database schema
- Suggests tables, columns, functions, and aliases
- Supports multi-table joins and subqueries
---
### ✍️ Intelligent SQL Editor
- Multi-tab SQL editing and execution
- Saved frequently used queries
- Deep integration with SQL Copilot
---
### 💬 Database Chatbot
- Built-in conversational AI assistant
- Automatically understands connected database schema
- Ask questions directly about tables and SQL
- Quickly locate field meanings and query ideas
---
### 📈 ClickHouse Monitoring (Deep Integration)
A native observability interface designed specifically for ClickHouse.
- Real-time metrics:
- Total queries
- Slow queries
- Error queries
- Active users
- Query latency trends (P50 / P95)
- Query throughput trends (QPM)
- Multi-dimensional filtering:
- User
- Database
- Query type
- Time range
---
### 🔐 ClickHouse Privileges (Deep Integration)
Native ClickHouse user and role management UI.
- Create, edit, and delete database users
- Create roles and configure grant relationships
- Configure:
- Login username and password
- Allowed host addresses
- Granted roles and default roles
- Supports cluster-level privilege operations (On Cluster)
- No need to manually write GRANT / CREATE USER SQL
---
## 🔌 Database Support
| Database | Status |
|--------------|---------------------|
| ClickHouse | ✅ Deeply integrated |
| PostgreSQL | 🚧 In development |
| MySQL | 🚧 Planned |
| DuckDB | 🚧 Planned |
| SQLite | 🚧 Planned |
---
## ⚙️ Tech Stack
- Next.js + React + Tailwind
- Drizzle ORM
- Multi-model AI SDK integration
- PGLite
- Resend
- Shadcn UI
- Monaco Editor
---
## 🎯 Who is it for?
- Data engineers
- Data analysts
- Database platform teams
- ClickHouse operations teams
---
## 🚀 Getting Started
> Docker one-click deployment
> Desktop client (Mac) coming soon
---
## 📄 License
Apache-2.0