toon and toon-crystal

These are ecosystem siblings where the TypeScript reference implementation provides the official specification and tooling while the Crystal version is an alternative language binding for the same serialization format standard.

toon
67
Established
toon-crystal
28
Experimental
Maintenance 13/25
Adoption 15/25
Maturity 22/25
Community 17/25
Maintenance 10/25
Adoption 5/25
Maturity 13/25
Community 0/25
Stars: 23,207
Forks: 1,033
Downloads:
Commits (30d): 1
Language: TypeScript
License: MIT
Stars: 9
Forks:
Downloads:
Commits (30d): 0
Language: Crystal
License: MIT
No risk flags
No Package No Dependents

About toon

toon-format/toon

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

TOON helps developers working with Large Language Models (LLMs) by providing a more compact and readable way to format structured data inputs. It takes existing JSON data and translates it into a token-efficient format that LLMs can process reliably, reducing both cost and potential errors. This is primarily useful for AI/ML engineers and data scientists preparing data for LLM prompts.

LLM-prompting AI-data-preparation token-optimization structured-data natural-language-processing

About toon-crystal

mamantoha/toon-crystal

Crystal implementation of the Token-Oriented Object Notation(TOON) serialization format

TOON (Token-Oriented Object Notation) is a compact, human-readable format for sending structured information to Large Language Models (LLMs) while using fewer tokens. It takes your existing data (like lists, tables, or nested objects) and converts it into a streamlined text format that LLMs can efficiently process. This is for developers working with Crystal who need to prepare data for LLM inputs.

LLM-input-preparation data-serialization token-optimization API-integration

Scores updated daily from GitHub, PyPI, and npm data. How scores work