token-optimizer-mcp
衡量每个AI编码智能体的token节省量，优化上下文，并在16个CLI客户端之间共享实时本地知识图谱。
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
怎么安装
npx -y @ooples/token-optimizer-mcp git clone https://github.com/ooples/token-optimizer-mcp ~/.claude/skills/token-optimizer-mcp 简介
and ships the benchmark so you can check it.</strong> --- Why it wins Providers cache the prompt prefix: cached tokens re-read at **0.1x**, rewritten ones bill at **1.25x**. Most compressors optimise bytes removed and ignore that multiplier. This one optimises the bill. **It wins both columns.** Against a faithful reimplementation of the leading open compressor's published design, node bench/compression/proof.mjs: node bench/compression/proof.mjs. Guarded by node bench/compression/readme-table.check.mjs; do not hand-edit. --> | workload | payload | theirs | ours | verdict | | -----------------…
推荐参考
信息
- 协议
- MIT
- 语言
- JavaScript
- GitHub 星标
- 535
- 月下载
- 8.6K
- 最近更新
- 2026-09-23
- 创建于
- 2025-10-11
基础安全检查
- 检查结果
- package.json 含 postinstall 脚本
- 收录来源
- curated:punkpeye/awesome-mcp-servers
- 主题标签
- ai, caching, claude, compression, gemini-cli-extension, llm, mcp, mcp-server, token-optimization
同类推荐
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23