| home |
Token-Oriented Object Notation |
| name |
text |
tagline |
image |
actions |
| TOON |
Token-Oriented Object Notation |
A compact, human-readable encoding of the JSON data model for LLM prompts. |
| dark |
light |
alt |
| /logo-index-dark.svg |
/logo-index-light.svg |
TOON Logo |
|
| theme |
text |
link |
| brand |
Get Started |
/guide/getting-started |
|
| theme |
text |
link |
| alt |
Benchmarks |
/guide/benchmarks |
|
| theme |
text |
link |
| alt |
CLI |
/cli/ |
|
| theme |
text |
link |
| alt |
Spec v2.1 |
/reference/spec |
|
|
|
| title |
icon |
details |
link |
| Token-Efficient & Accurate |
📊 |
TOON reaches 74% accuracy (vs JSON's 70%) while using ~40% fewer tokens in mixed-structure benchmarks across 4 models. |
/guide/benchmarks |
|
| title |
icon |
details |
link |
| JSON Data Model |
🔁 |
Encodes the same objects, arrays, and primitives as JSON with deterministic, lossless round-trips. |
/guide/format-overview |
|
| title |
icon |
details |
link |
| LLM-Friendly Guardrails |
🛤️ |
Explicit [N] lengths and {fields} headers give models a clear schema to follow, improving parsing reliability. |
/guide/format-overview#arrays |
|
| title |
icon |
details |
link |
| Minimal Syntax |
📐 |
Uses indentation instead of braces and minimizes quoting, giving YAML-like readability with CSV-style compactness. |
/guide/format-overview#arrays |
|
| title |
icon |
details |
link |
| Tabular Arrays |
🧺 |
Uniform arrays of objects collapse into tables that declare fields once and stream row values line by line. |
/guide/format-overview#arrays |
|
| title |
icon |
details |
link |
| Multi-Language Ecosystem |
🌐 |
Spec-driven implementations in TypeScript, Python, Go, Rust, .NET, and other languages. |
/ecosystem/implementations |
|
|
