Skillget

zenku-v2

mcp
Security Audit
Warn
Health Pass
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 30 GitHub stars
Code Warn
  • network request — Outbound network request in docker-compose.yml
  • process.env — Environment variable access in packages/server/src/ai/index.ts
  • process.env — Environment variable access in packages/server/src/ai/ollama-models.ts
  • network request — Outbound network request in packages/server/src/ai/ollama-models.ts
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This is an AI-powered, no-code engine that allows developers to build production-ready data applications through natural language. It uses a multi-agent architecture to dynamically generate and manage database schemas, user interfaces, and business logic.

Security Assessment
Overall Risk: Medium. The tool does not request dangerous system permissions or execute arbitrary shell commands. However, there are a few security considerations to note. It makes outbound network requests, primarily to communicate with external AI models like Ollama. The codebase also accesses environment variables to handle sensitive configuration and API keys safely, rather than hardcoding them, which is a good practice. Because the application acts as an engine to directly modify database schemas and execute logic, it inherently accesses and controls sensitive data structures.

Quality Assessment
The project appears to be actively maintained, with its most recent push happening today. It has a small but growing community footprint, evidenced by 30 GitHub stars. The repository includes comprehensive documentation and a well-structured monorepo setup using TypeScript. The only downside is that the license is marked as "NOASSERTION," meaning you will need to verify the exact open-source terms in the repository before utilizing it for commercial enterprise applications.

Verdict
Use with caution — while the code avoids dangerous permissions and hardcoded secrets, verify its open-source license and ensure outbound AI network requests align with your data privacy policies.
SUMMARY

AI-first No-Code engine for building production-ready data apps via conversation. Features Multi-Agent architecture, dynamic UI rendering, and built-in Undo/Time-Machine. Supports SQLite, Postgres, and MSSQL.

README.md

Zenku

Build Production-Ready Data Apps via Conversation.

繁體中文 | Documentation

Zenku Light Theme Screenshot

Zenku is an AI-first, open-source No-Code Engine designed for building enterprise-grade data applications. Instead of generating static code, Zenku uses a sophisticated Multi-Agent Architecture to dynamically evolve your database schema, UI views, and business logic in real-time through natural language.

  • Chat-to-App Workflow: Transform "I need a CRM" into a live system (Schema -> CRUD UI -> Dashboard) in seconds.
  • Specialist Agent System: Dedicated agents for Schema, UI, Logic, Query, and Testing, coordinated by a central Orchestrator.
  • Enterprise DB Support: Native support for SQLite, PostgreSQL, and Microsoft SQL Server (MSSQL).
  • Versatile View Engine: Dynamic rendering for Kanban, Gantt, Calendar, Timeline, Dashboard, and more.
  • Real-time Logic: A powerful Business Rules Engine for automation, validation, and third-party webhooks (e.g., n8n).
  • Reliability & Undo: A built-in Design Journal acting as a "Time Machine," allowing you to undo any AI change instantly.
  • MCP Ready: Full Model Context Protocol support, enabling external AI tools to control your Zenku instance.

🧠 Architecture: The Multi-Agent Orchestrator

Unlike simple "Code Gen" wrappers, Zenku separates reasoning from execution through specialized roles:

graph TD
    User[User] <--> Orch[Orchestrator Agent]
    Orch <--> Schema[Schema Agent]
    Orch <--> UI[UI Agent]
    Orch <--> Query[Query Agent]
    Orch <--> Logic[Logic Agent]
    Orch <--> Test[Test Agent]

🏗️ Architecture

Zenku uses a Monorepo (npm workspaces) structure:

1. @zenku/server (The Brain)

  • Stack: Node.js + Express + TypeScript
  • Database Layer: Robust Adapter pattern for switching between production-grade databases.
  • Orchestrator: Coordinates specialized LLM Tool Agents:
    • schema-agent (DDL & Schema Management)
    • ui-agent (View Definition & Layout)
    • query-agent (Natural Language to SQL)
    • logic-agent (Automation Rules & Guardrails)

2. @zenku/web (The Interpreter)

  • Stack: React 19 + Vite + Tailwind CSS + shadcn/ui
  • Dynamic Rendering: Composed of highly abstract components (TableView, FormView, GanttView) that render instantly based on JSON definitions.

3. @zenku/shared (Common Ecosystem)

  • Strictly maintained TypeScript definitions, Formula calculation engine, and Appearance logic parser.

🚀 Quick Start

1. Developer Setup

  1. Install Dependencies:

    git clone https://github.com/antonylu0826/zenku-v2.git
cd zenku
npm install

  2. Configure Environment:
    Copy .env.example to .env and fill in your API Key and DB credentials:

    # Example: Switch to MSSQL
DB_TYPE=mssql
DB_HOST=localhost
DB_USER=sa
DB_PASSWORD=YourPassword

  3. Launch:

    npm run dev

    Visit http://localhost:5173 to start.

2. One-Click Docker Deployment

docker-compose up -d

3. Build Your First App in 5 Minutes

  • Project Management:
    "Create a project tracking system with name, progress, start and end dates, and generate a Gantt chart view for me."
  • Automation & Validation:
    "In the order form, if stock is less than demand, prevent saving and show an 'Insufficient Stock' warning."
  • Workflow Integration:
    "When a new order is created, trigger a webhook to my n8n workflow."

Zenku aims to unleash your creativity by turning complex development into a simple, fun conversation. Happy Building! 🚀

📚 Documentation

For more technical details and implementation guides, please refer to our official documentation:

  • English Documentation: Includes core concepts, architecture design, functional specs, and n8n integration guides.
  • 繁體中文文檔: Conceptual overview, system architecture, and API references in Traditional Chinese.

📄 License

This project is licensed under the GPL v3 License.

Reviews (0)

No results found