ScriptRAG is a novel screenwriting tool that combines Fountain parsing, graph databases, and local LLMs to create an intelligent screenplay assistant using the GraphRAG (Graph + Retrieval-Augmented Generation) pattern.
- Installation Guide - Get ScriptRAG up and running
- User Guide - Complete guide for screenwriters
- Usage Examples - Common workflows and examples
- Bulk Import Guide - Import multiple screenplays
- MCP Usage Examples - Using with AI assistants
- Developer Guide - Contributing to ScriptRAG
- Architecture Overview - System design and patterns
- API Reference - Complete API documentation
- MCP Server Documentation - Model Context Protocol integration
- AI Agent Guidelines - Guidelines for AI contributors
- Claude Coding Guidelines - Coding standards and workflows
- Python 3.11+
- uv package manager
- SQLite 3.38+ (for vector support)
- LMStudio running at http://localhost:1234
# Clone the repository
git clone https://github.com/trieloff/scriptrag.git
cd scriptrag
# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh
# Set up development environment
make setup-dev
# Initialize the database
make db-init
# Activate the virtual environment
source .venv/bin/activate# Parse a screenplay
scriptrag script import path/to/screenplay.fountain
# Search for scenes
scriptrag scene search "coffee shop"
# Start the MCP server
scriptrag mcp startSee the User Guide for complete documentation.
- Language: Python with uv package manager
- Database: SQLite as a graph database
- LLM: Local LLMs via LMStudio (OpenAI-compatible API)
- Parser: Fountain screenplay format parser
- Pattern: GraphRAG (Graph + Retrieval-Augmented Generation)
- Interface: MCP (Model Context Protocol) server
Contributions are welcome! Please see our Developer Guide and AI Agent Guidelines for more details.
This project is licensed under the MIT License - see the LICENSE file for details.