toon-format/toon
Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks. Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: 🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
Stars
25k
Last 24h
+72est.
Last 7 days
+502est.
Forks
1.1k
Star history (last 1 snapshot)
Only one snapshot so far. The chart fills in as OSS Radar collects daily snapshots.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/toon-format/toon)<a href="https://ossradar.net/repo/toon-format/toon"><img src="https://ossradar.net/badge/toon-format/toon" alt="Trending on OSS Radar"></a>About toon
toon-format/toon is a TypeScript project in the LLM tooling category, created 12 months ago. It has 25k GitHub stars and 1.1k forks, and gained +502 stars over the last 7 days (early estimate), ranking #82 of 167 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- TypeScript
- Category
- LLM tooling
- Created
- Oct 22, 2025
- Last push
- Oct 9, 2026
- data-format
- llm
- serialization
- tokenization
Similar rising repos
- KKKKhazix/AIHOT+3.6kest.
一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的,它就是你的行业热点站。 Why it matters: useful plumbing for shipping LLM-powered features.
- lidge-jun/opencodex+1kest.
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude… Why it matters: useful plumbing for shipping LLM-powered features.
- langgenius/dify+866est.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so… Why it matters: useful plumbing for shipping LLM-powered features.
- can1357/oh-my-pi+864est.
⌥ Coding agent with the IDE wired in. Built by Stencil Labs. Why it matters: useful plumbing for shipping LLM-powered features.
- upstash/context7+780est.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors. Why it matters: useful plumbing for shipping LLM-powered features.
- trailhq/Trail-Code+683est.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase. Why it matters: useful plumbing for shipping LLM-powered features.