davidpirogov/toon-llm
Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.
This project helps you structure your Python data—like dictionaries, lists, or Pydantic models—into a compact, human-readable format optimized for large language models (LLMs). It takes your standard Python data and outputs a special text format that significantly reduces the 'token count' when fed into an LLM, making your AI interactions faster and more cost-effective. Data scientists, AI engineers, and anyone working with LLMs will find this useful for efficient prompt engineering.
Available on PyPI.
Use this if you need to pass complex structured data from Python into an LLM and want to minimize token usage, improve LLM comprehension, and reduce API costs.
Not ideal if your primary goal is data exchange with systems that only understand standard JSON, or if you are not working with LLMs.
Stars
9
Forks
3
Language
Python
License
MIT
Category
Last pushed
Oct 31, 2025
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/davidpirogov/toon-llm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PacktPublishing/Mastering-NLP-from-Foundations-to-LLMs
Mastering NLP from Foundations to LLMs, Published by Packt
HandsOnLLM/Hands-On-Large-Language-Models
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
mlabonne/llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
louisfb01/start-llms
A complete guide to start and improve your LLM skills in 2026 with little background in the...
Denis2054/Transformers-for-NLP-and-Computer-Vision-3rd-Edition
Transformers 3rd Edition