Skip to content

gmh5225/scriptrag

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

853 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ScriptRAG: A Graph-Based Screenwriting Assistant

90% Vibe_Coded

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.

📚 Documentation

For Users

For Developers

🚀 Quick Start

Prerequisites

  • Python 3.11+
  • uv package manager
  • SQLite 3.38+ (for vector support)
  • LMStudio running at http://localhost:1234

Installation

# 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

Basic Usage

# Parse a screenplay
scriptrag script import path/to/screenplay.fountain

# Search for scenes
scriptrag scene search "coffee shop"

# Start the MCP server
scriptrag mcp start

See the User Guide for complete documentation.

Tech Stack

  • 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

Contributing

Contributions are welcome! Please see our Developer Guide and AI Agent Guidelines for more details.

License

This project is licensed under the MIT License - see the LICENSE file for details.

References

About

A Graph-Based Screenwriting Assistant that combines Fountain parsing, graph databases, and local LLMs using the GraphRAG pattern

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 92.0%
  • Shell 5.5%
  • Makefile 2.5%