# toon-format/toon

🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

Repository: https://github.com/toon-format/toon
Canonical: https://ross.abutalabs.com/products/toon
Homepage: https://toonformat.dev
Language: TypeScript
License: MIT
License Family: permissive
Topics: data-format, llm, serialization, tokenization
Last push: 2026-08-23T08:37:43+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 22
- inputs: {"age_days": 315, "days_push": 10, "days_rel": 28, "gap_med": 1.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 25261, forks 1121 (observed 2026-08-28T04:11:38.085415+00:00)

## What it is
TOON (Token-Oriented Object Notation) is a compact, human-readable encoding of the JSON data model designed to reduce token usage in LLM prompts while remaining lossless and deterministic. It ships as a TypeScript SDK, a CLI, and benchmarks, with a shared spec and conformance suite across many language implementations.

## Use cases
- reduce token costs when passing JSON data to LLM prompts
- encode uniform arrays of objects compactly for model input
- convert JSON to a more token-efficient format and back losslessly
- benchmark token efficiency of data formats for LLMs
- validate LLM output structure with explicit array lengths and field lists

## When to choose
- your prompts embed large JSON payloads, especially uniform arrays of objects
- you want a lossless, deterministic JSON alternative optimized for token count
- you need a spec with multi-language implementations and conformance tests

## When to avoid
- your data is deeply nested and heterogeneous, where JSON or YAML may be comparable
- you need a general-purpose serialization format for storage or APIs rather than LLM input
- your pipeline requires strict JSON tooling compatibility

## Facets
- artifact type: library
- maturity: active
- function: serialization, llm-inference, prompt-engineering, cli, benchmarking
- domain: large-language-models, developer-tools, apis
- platform: cli, cross-platform
- tags: data-format, token-efficiency, json-encoding, llm-prompts, tokenization, data-engineering, nodejs, typescript

## Member repositories
- toon-format/toon (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.085415+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:04.623473+00:00, confidence not recorded.
  - readme: https://github.com/toon-format/toon (fetched 2026-08-28T04:11:38.085415+00:00, sha 63ed34a92f80)
  - homepage: https://toonformat.dev (fetched 2026-08-29T07:53:19.471291+00:00, sha f53a63c2f085)
  - site_page: https://toonformat.dev/guide/getting-started.html (fetched 2026-08-29T07:53:19.474928+00:00, sha fb01668e2bfa)
- Data as of 2026-08-30T08:39:29.467469+00:00.