totoon 0.1.0

Convert any data format to TOON (Token-Oriented Object Notation)

totoon

totoon - Convert any data format to TOON (Token-Oriented Object Notation)

TOON is a compact data format that reduces token usage by 30-60% compared to JSON when interfacing with Large Language Models (LLMs).

Features

• 🚀 Convert JSON, YAML, XML, and more to TOON format
• 📦 Multi-language SDK support (starting with Python)
• ⚡ High-performance conversion
• 🔧 Easy to integrate
• 📚 Comprehensive documentation

Installation

Python

pip install totoon

Quick Start

Python

from totoon import to_toon

# Convert Python dict to TOON
data = {
    "users": [
        {"name": "Alice", "age": 30},
        {"name": "Bob", "age": 25}
    ]
}

toon_output = to_toon(data)
print(toon_output)

Output:

users:
  name | age
  --- | ---
  Alice | 30
  Bob | 25

Convert from JSON

from totoon import json_to_toon

json_str = '{"name": "Alice", "age": 30}'
toon_output = json_to_toon(json_str)
print(toon_output)

Convert from YAML

from totoon import yaml_to_toon

yaml_str = """
users:
  - name: Alice
    age: 30
  - name: Bob
    age: 25
"""
toon_output = yaml_to_toon(yaml_str)
print(toon_output)

Why TOON?

TOON (Token-Oriented Object Notation) is designed specifically for LLM interactions:

• 30-60% token reduction compared to JSON
• Tabular format for arrays of objects (common in LLM data)
• Human-readable while being compact
• Efficient for API calls to LLMs

Example Comparison

JSON:

{
  "users": [
    {"name": "Alice", "age": 30},
    {"name": "Bob", "age": 25}
  ]
}

~80 tokens

TOON:

users:
  name | age
  --- | ---
  Alice | 30
  Bob | 25

~35 tokens (56% reduction!)

Supported Formats

• ✅ JSON
• ✅ YAML
• ✅ XML
• 🔄 CSV (coming soon)
• 🔄 TOML (coming soon)

Language Support

• ✅ Python
• ✅ JavaScript/TypeScript
• ✅ Go
• ✅ Rust

Repository

• GitHub: https://github.com/bug4fix/totoon
• Issues: https://github.com/bug4fix/totoon/issues
• Discussions: https://github.com/bug4fix/totoon/discussions

License

MIT License - See LICENSE file for details

Contributing

Contributions are welcome! Please read our Contributing Guidelines.

Business Model

This project follows an Open Source + Enterprise SaaS model:

• Open Source: Core SDKs are free and open source
• Enterprise: Cloud API, advanced features, and support available for enterprise customers (coming soon)