toon-format
Token-Oriented Object Notation – a token-efficient JSON alternative for LLM prompts
Decision gist · record as of 2026-08-14
No, not yet. The package is currently a namespace reservation with full implementation pending. While the concept is sound and the MIT license is permissive, installing 0.1.0 will not provide working encode/decode functions. Wait for a later release that completes the implementation before adopting this package.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; package is currently in alpha and full implementation is not yet complete.
- Low friction install with no runtime dependencies.
- The package is actively maintained and supports modern Python versions (3.10–3.14), though it is currently in alpha status and marked as a namespace reservation with full implementation pending.
License · maintenance · safety
MIT (permissive) — MIT license permits free use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.
last release 2025-11-01 (286 days) · last repo commit 2026-05-20 · 757 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 548,263 downloads/mo, #6,065 on PyPI
Alternatives
Verify before relying
pip install toon-format
from toon_format import encode, decode
data = {"users": [{"id": 1, "name": "Alice"}]}
toon_string = encode(data)
decoded = decode(toon_string)- Whether encode() and decode() functions are currently implemented or if the package is still a placeholder.
- Performance benchmarks comparing token reduction versus JSON for typical LLM use cases.
- Compatibility with specific LLM APIs or frameworks beyond the general use case.
What it is and what it does
TOON Format is a Python implementation of Token-Oriented Object Notation, a serialization format that compresses structured data into a more compact representation than JSON. It is designed specifically for reducing token consumption when sending data to language models, where token count directly affects cost and latency. The format uses a column-oriented syntax that eliminates redundant key names and whitespace, allowing the same data to fit in fewer tokens.
The package provides encode() and decode() functions to convert between Python data structures and TOON strings. However, the current release (0.1.0) is marked as a namespace reservation, meaning the core implementation is not yet complete. It supports Python 3.10 through 3.14 and has no external runtime dependencies, making installation straightforward once the implementation is ready.
Use it for
- Reduce token count in LLM API calls by encoding structured data in TOON format before sending prompts.
- Serialize configuration or metadata objects for embedding in language model contexts with minimal overhead.
- Convert between JSON and TOON formats to optimize data passed to AI systems where token budgets are constrained.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
No, not yet.
The package is currently a namespace reservation with full implementation pending. While the concept is sound and the MIT license is permissive, installing 0.1.0 will not provide working encode/decode functions. Wait for a later release that completes the implementation before adopting this package.
Install
toon-format on PyPI
Before you install
Low friction install with no runtime dependencies. The package is actively maintained and supports modern Python versions (3.10–3.14), though it is currently in alpha status and marked as a namespace reservation with full implementation pending.
Requires Python 3.10 or later; package is currently in alpha and full implementation is not yet complete.
License in practice
MIT license permits free use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.
Quickstart
pip install toon-format
from toon_format import encode, decode
data = {"users": [{"id": 1, "name": "Alice"}]}
toon_string = encode(data)
decoded = decode(toon_string)Verify before relying
- Whether encode() and decode() functions are currently implemented or if the package is still a placeholder.
- Performance benchmarks comparing token reduction versus JSON for typical LLM use cases.
- Compatibility with specific LLM APIs or frameworks beyond the general use case.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 286 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 548,263 / month, #6,065 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 3 - AlphaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Libraries :: Python Modules |
Evidence: toon_format-0.1.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “token-efficient data format”
- toon-formatEncodes and decodes data structures using TOON (Token-Oriented Object…
- python-toonEncodes and decodes TOON (Token-Oriented Object Notation), a compact…
- toonstoons is a Rust-backed Python parser and serializer for the TOON…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also python-toon · toons · doclang · py-ubjson · dataclasses-json · banks · simplejson · json-flatten · dataclasses-json-speakeasy · avro