dineug/erd-editor

Design database schemas as ERDs in your browser, VS Code, JetBrains IDEs or Obsidian. Import SQL, DBML and GraphQL, export DDL and code, and let coding agents edit live over MCP.

What it solves

ERD Editor provides a unified, visual environment for designing database schemas. It solves the fragmentation of database modeling by offering a consistent experience across web browsers, IDEs (VS Code, JetBrains), and note-taking apps like Obsidian, while enabling AI coding agents to participate in the design process.

How it works

It uses a single .erd.json file format to represent database schemas. The project includes a core custom element (<erd-editor>) that renders the visual diagram. For AI integration, it provides an MCP (Model Context Protocol) server that allows coding agents like Claude Code or Codex to read, modify, and collaborate on the schema directly within the editor's canvas.

Who it’s for

It is for developers and database architects who need to design, visualize, or modify database schemas and want to integrate those workflows into their existing IDEs or leverage AI agents to automate schema updates.

Highlights

  • Multi-platform support: Works as a web app, VS Code/JetBrains extension, Obsidian plugin, and Google Drive app.
  • AI-Ready: Includes an MCP server that allows AI agents to act as collaborators, making edits directly to the visual schema.
  • Extensive Import/Export: Supports importing SQL DDL, GraphQL SDL, and DBML, with exports for 8 database types and 22 programming languages/ORMs.
  • Real-time Collaboration: Features WebRTC-based, encrypted live sessions for team editing.
  • Embeddable: Provides a custom element (<erd-editor>) for developers to embed the modeling tool into their own applications.

Related

  • Project
    donvito/codex-astra-luna-orchestrator

    A plug‑in for the Codex CLI that installs pre‑configured multi‑agent orchestration profiles (Astra, Sol, Luna) so a project can automatically plan, code, test, and review changes using GPT‑6 sub‑agents.

  • Project
    gi-dellav/zerostack

    zerostack is a lightweight coding agent written in Rust that runs in the terminal, supporting multiple LLM providers. It offers granular permission controls, session management, subagents, and optional persistent memory, while using far less RAM and CPU than JavaScript-based agents.

  • Project
    matlab/matlab-mcp-server

    MATLAB MCP Server is a Go‑based bridge that lets AI assistants (Claude, Copilot, Codex, etc.) start MATLAB, run scripts, perform static analysis, and run unit tests via the Model Context Protocol. It supports configurable launch options, custom tool extensions, and provides coding‑guideline resources. Install MATLAB R2021a+, download the binary, and integrate it with your AI tool using the provided CLI snippets.

  • Project
    patoles/agent-flow

    Agent Flow is a real‑time visual debugger for Claude Code and Codex AI agents. It streams execution events via a lightweight hook (Claude) or Codex rollout logs, and displays them as an interactive node‑graph with timeline, transcript, and heat‑map panels. Available as a standalone web app (`npx agent-flow-app`), a VS Code extension, or a dev server, it supports multi‑session tabs, JSONL replay, and runtime selection. Designed to make agent reasoning, tool‑call chains, and performance visible for debugging and prompt‑engineering, it ships with optional anonymous telemetry and is Apache‑2.0 licensed.