搜索关键词:prompt-compression,共找到 3 个结果
排序方式:
当前按 更新时间 降序 排列

mfonte/fast-toon

Fastest TOON (Token-Oriented Object Notation) encoder/decoder for PHP 7.0+. 3x faster encoding, 15x faster decoding vs alternatives. LLM-optimized with ~40% token reduction vs JSON.

版本:v1.0.0 下载:3 Stars:0 点击:5

时间:2025-12-22 17:02

helgesverre/toon

Token-Oriented Object Notation - A compact data format for reducing token consumption when sending structured data to LLMs

版本:v3.1.0 下载:9.27k Stars:97 点击:2

时间:2025-10-27 14:53

sbsaga/toon

???? TOON for Laravel — a compact, human-readable, and token-efficient data format for AI prompts & LLM contexts. Perfect for ChatGPT, Gemini, Claude, Mistral, and OpenAI integrations (JSON ⇄ TOON).

版本:v1.2.0 下载:1.66k Stars:46 点击:7

时间:未知