davidpirogov/toon-llm
Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.
Automatically serializes Python native types (datetime, dataclasses, Pydantic models) while intelligently selecting array formatting—inline, tabular, or list—to minimize token overhead. Achieves 60%+ token reduction versus JSON through syntax minimization and structural clarity, making it particularly effective for embedding structured data in LLM prompts. Includes CLI tooling for encoding/decoding with configurable delimiters and indentation, plus full Pydantic validation support for type-safe data handling.
9 stars and 17,450 monthly downloads. Available on PyPI.
Stars
9
Forks
3
Language
Python
License
MIT
Category
Last pushed
Oct 31, 2025
Monthly downloads
17,450
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.
Related models
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