factory-gen.com

Overview

FactoryGen is a full-stack AI-powered workflow automation platform that combines a modern web interface with desktop application capabilities. It enables users to build and manage complex workflows using a visual node-based canvas, where workflows are constructed by connecting different node types (triggers, inputs, AI processors, and outputs). The platform leverages Convex as its real-time backend and database, providing seamless synchronization and robust data management for workflow execution and interaction.

The project is designed to simplify workflow creation for users who need to orchestrate AI-powered tasks without writing code, using an intuitive drag-and-drop visual interface.

Architecture

The project is split across three layers:

• Web frontend (src-next) — Next.js app with the visual workflow canvas and React components
• Desktop app (src-tauri) — Tauri wrapper that embeds the web frontend and exposes native system capabilities via Rust
• Convex backend — unified backend handling the database, real-time updates, and serverless functions for workflow and AI tasks

Core Workflow Features

Visual Workflow Canvas

• Intuitive Node-Based Interface: Drag-and-drop visual interface using React Draggable and Framer Motion animations
• AI-Assisted Workflow Creation: Automatically generates entire workflow graphs from user descriptions
• Node-Based Architecture: Modular workflow system with four primary node types:
  • Trigger Nodes: Webhook, cron, file change, and HTTP request triggers for workflow initiation
  • Input Nodes: Data input collection from external sources
  • AI Nodes: LLM integration with support for multiple providers (Anthropic, OpenAI, Google) via Vercel's AI SDK
  • Output Nodes: Results and data output handling

AI & Automation Capabilities

• Multi-Provider AI Support: Integration with Anthropic Claude, OpenAI, and Google models
• OpenRouter Integration: Access to multiple models through OpenRouter API with reasoning model support (Mercury model)
• Node Generation: AI-powered automatic node creation based on user prompts
• Parameter Configuration: Dynamic parameter management with validation for each node
• Workflow Execution Logging: Real-time execution tracking with detailed logs and debug information

Trigger & Execution

• Multiple Trigger Types:
  • Webhook triggers with secret authentication
  • Cron-based scheduled execution
  • File system change detection
  • HTTP request triggers
• Execution Status Tracking: Real-time workflow execution monitoring with success/failure states
• Execution History: Tracking of trigger executions with timestamps and payloads

Data & Persistence

• Convex Real-Time Database: Persistent storage for workflows, nodes, edges, and execution data
• Workspace Management: Multi-workspace support for organizing workflows
• Parameter Validation: Comprehensive validation for node parameters (string, number, boolean, JSON, array types)
• Global Workflows: Support for both workspace-specific and globally accessible workflows

Frontend Features

• Multi-Page Application:
  • Dashboard with workflow management
  • Workflow editor with canvas
  • New workflow creation wizard
  • Logs viewer for execution history
  • Debug panel for workflow troubleshooting
• Sidebar Navigation: Workspace switcher and workflow organization
• Real-Time Updates: Convex synchronization provides live updates across all connected clients

Desktop Integration

• Tauri Desktop Application: Cross-platform desktop app (Windows, macOS, Linux) that embeds the web frontend
• Native System Integration: Direct access to system resources including:
  • File system operations (read/write)
  • Clipboard management
  • Notifications
  • Global keyboard shortcuts
  • Process execution
  • HTTP requests
  • Dialog interactions
  • OS information

Use Cases

FactoryGen is ideal for:

• Automation Enthusiasts: Users who want to create AI-powered workflows without coding experience
• Teams Needing Automation: Organizations automating repetitive tasks across systems
• AI Integration Specialists: Developers integrating multiple AI providers into cohesive workflows
• Content Creators: Automating content generation, processing, and distribution
• Business Process Automation: Teams automating document processing, data transformation, and business logic
• System Administrators: Automating system maintenance tasks and scheduled operations
• No-Code/Low-Code Users: Users preferring visual programming over traditional code-based approaches

The platform bridges the gap between simple automation tools and complex workflow orchestration systems, making it accessible to both technical and non-technical users.

What I learned

The hardest part was keeping the visual canvas in sync with backend state in real time without the UI feeling sluggish. Convex's reactive queries helped, but knowing when to optimistically update the canvas versus waiting for confirmation required a lot of trial and error.

The Tauri + Next.js combination also pushed me to think carefully about which logic belongs at the native layer versus the web layer — especially for anything involving the filesystem or running local processes.

Tech Stack

Frontend

• Framework: Next.js 16.1.6 (App Router with Server Components)
• UI Library: React 19.2.4
• Styling: Tailwind CSS 4, PostCSS 4
• Animation: Framer Motion 12.35.1
• UI Components: Lucide React, React Icons, custom ui-lab-components
• Drag & Drop: React Draggable 4.5.0
• Type Safety: TypeScript 5, Zod 4.3.6
• State Management: Convex Client for real-time database syncing, React Context API

Backend

• Backend Platform: Convex (serverless backend)
• Runtime: Node.js (v18.x or later)
• Database: Convex real-time database
• AI Integration:
  • Vercel AI SDK 6.0.105 (unified AI provider interface)
  • @ai-sdk/anthropic 3.0.58
  • @ai-sdk/openai 3.0.37
  • @ai-sdk/google 3.0.43
  • OpenRouter (for extended model access with Mercury reasoning)

Desktop Application

• Framework: Tauri 2
• Runtime: Rust (Cargo)
• Plugins: Global shortcuts, HTTP requests, OS info, notifications, clipboard, file system, shell commands

Development Tools

• Package Manager: pnpm (monorepo management)
• Testing: Vitest 4.0.18, Playwright 1.58.2
• Linting: ESLint 9
• Build Tools: TypeScript 5, Cargo