ModelForge is a comprehensive platform that brings next-gen AI capabilities to Blender through integrated components:

• Gemini 3 Pro Orchestration: Advanced ReAct-style planner with per-step validation
• Smart Material Application: Automatic material assignment and validation
• Scene Auditing: Ensures lighting, camera, and base materials exist with auto-correction

• Context-Aware Generation: Leverages 113+ professional Blender scripts for accurate code generation
• Semantic Search: Uses Together.ai M2-BERT embeddings for high-quality retrieval
• Knowledge Base: Covers modeling, rigging, shading, geometry nodes, and animation

• User Authentication: Secure NextAuth.js v5 with Google OAuth
• Project Management: Track multiple Blender projects
• Asset Integration: Toggles for Poly Haven, Hyper3D Rodin, and Sketchfab

• Socket Bridge: Executes generated Python directly in Blender
• Real-time Communication: Live feedback from Blender operations
• External Integration: Compatible with blender-mcp

Frontend	Next.js 16 • React 19 • TypeScript 5.6 • Tailwind CSS
Backend	Node.js 24+ • Prisma 5.20 • PostgreSQL 14+ (Neon)
AI & Desktop	Gemini 3 Pro • LangChain • Electron • Blender API

• Node.js 18+ (24+ recommended)
• PostgreSQL 14+ with vector extension (or Neon)
• Blender 3.0+
• Python 3.10+
• uv package manager

1. Clone the repository

   git clone https://github.com/Ker102/ModelForge.git
   cd ModelForge

2. Install dependencies

   npm install

3. Set up environment variables

   cp .env.example .env

   Configure .env with your Database URL, NextAuth secret, Gemini API key, and Together.ai API key (for RAG).

4. Initialize Database

   npm run db:generate
   npm run db:push

5. Ingest RAG Knowledge (Optional but recommended)

   npm run ingest:blender

6. Start development server

   npm run dev

   Open http://localhost:3000 in your browser.

Main tables:

• users: Accounts and auth
• projects: Blender projects
• conversations: Chat history
• document_embeddings: RAG knowledge base (pgvector)
• project_snapshots: Scene state

• Gemini-backed conversational planning
• Detailed plan auditing (components, materials, lighting)
• Electron desktop shell
• Hybrid RAG Pipeline (Neon + Together.ai)
• Expanded Script Library (113+ scripts)
• Conversation memory with vector embeddings
• Viewport screenshot analysis
• Production desktop app packaging

We welcome contributions! Please read our Contributing Guide to get started.

This project is licensed under the LICENSE file.