#18 · Primary category： LLM Application Frameworks
toon
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
Project last updated：08/23/26
GitHub Stars
25.3K
Forks
1.1K
Contributors
46
License
MIT
Why we included this project
TOON is a serialization format aimed at anyone who feeds structured data into LLM prompts. It encodes the JSON data model into a compact, indentation-based notation that spends fewer tokens on structure, stays lossless, and is easier for models to parse. The TypeScript SDK and CLI act as a translation layer: you keep JSON in your code and only encode to TOON at the prompt boundary. It works best on uniform, tabular data like lists of records, where it approaches CSV-level compactness while keeping explicit field lists and lengths that help models follow a schema. If your prompt pipelines send the same shaped data repeatedly, this trims cost without changing your data model.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform