Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integration. Achieves 2-10x productivity gains through systematic command organization and hierarchical configuration.

Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verification

💰 Save money on AI API costs! 76% token reduction, Auto-Fix token limits, Universal AI compatibility. Cline • Copilot • Claude • Cursor

Intelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence

Token-efficient log file system - reduce AI coding assistant context bloat by 93%

Context-optimized MCP server for web scraping. Reduces LLM token usage by 70-90% through server-side CSS filtering and HTML-to-markdown conversion.

Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

ASAN: A conceptual architecture for a self-creating (autopoietic), energy-efficient, and governable multi-agent AI system.

🚀 专为大模型优化的文本预处理工具 | AI Text Optimizer for reducing LLM token consumption

Smart Context Optimization for LLMs - Reduce tokens by 66%, save 40% on API costs. Intelligent ranking and selection of relevant context using embeddings, keywords, and semantic analysis.

pymdt2json is a Python CLI and library for converting markdown tables into structured JSON: ideal for data pipelines, LLM preprocessing, and web/API integration.

A lightweight, fast TOON (Token-Oriented Object Notation) library for PHP. Optimized for LLM contexts. PHP 7.0-8.0 [legacy] and 8.1 and up [modern] support.

MCP server gateway for Claude Code, Claude Desktop, and Cline. Loads only specific tools from your MCPs as you need them and saves thousands of tokens. Works with any Model Context Protocol server.

A memory compression engine built for AI — modular, dual-mode (Compact or Expressive), and part of Nova OS in development. Designed for scalable memory and token efficiency while preserving meaning.

Launching CRAFT Framework Alpha. What if AI could understand Object-Oriented Programming? That's what I'm building. Follow for updates. OOP + AI = CRAFT

A standard protocol for managing large artifacts and context in LLM sessions

Structured AI development workflow system for Claude Code with specialized agents - Prevents vibe coding, enforces planning, maintains context

Reusable setup prompts for optimizing Claude Code documentation. Achieve 90% token savings on any project in 5 minutes.

a technique for compressing verbose AI tool call outputs into concise summaries, reducing token consumption