⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

CodeGrok MCP is a Model Context Protocol (MCP) server that enables AI assistants to intelligently search and understand codebases using semantic embeddings and Tree-sitter parsing.

Lightweight, agent-optimized database CLI with one-shot schema introspection, column profiling, and ERD generation.

Skim: A MCP server for Claude Code — skim large outputs, return only schema. Save context, save tokens.

GitHub Action that analyzes codebases and generates AI agent context documentation (CLAUDE.md/AGENTS.md) to optimize AI coding assistant efficiency. Reduces token waste and improves development velocity through intelligent recommendations.

13 production microservices that prevent wasteful AI API calls through semantic search, caching, and team learning - 85% cost reduction

🎯 Optimize LLM token usage by 70-90% with smart context ranking, reducing costs while maintaining quality and performance.

Comprehensive cognitive infrastructure for AI-augmented development and knowledge work

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.

Source-available MCP server for context optimization, agent memory, and self-hosted AI workflows.

Graph-style library for LLM agents: plan → fetch context → synthesize → verify.

COSE-461 자연어처리 25-1 Final Project

ContextFusion is the context brain for LLM apps - compress, rank, and route the right evidence to chat + agent models across OpenAI, Claude, Ollama, and MCP

distills Python repositories into compact review bundles for LLMs and agents

AST-powered AI reviewer; Groq x Llama.

Session Intelligence MCP Server - Lean meta-tool pattern with 95% context reduction

Agent Knowledge Cube — 三维知识约束框架: 角色(X) × 工作流(Y) × 知识库(Z)，让AI Agent在结构化边界内各司其职