Reliable LLM outputs start with clean context. Deterministic deduplication, compression, and caching for RAG pipelines.

The open source, no-code MCP Server for AI-Native API Access

Save context for what matters. The last agent you'll ever need.

Open-source AI gateway written in Rust, with token compression for Claude Code, Codex... and any other LLM client.

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

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.

Copilot Context Optimizer is a VS Code extension that gives GitHub Copilot specialized tools to analyze files and process terminal commands efficiently without overwhelming chat context. It extracts only specific information needed instead of dumping entire files or verbose outputs, keeping conversations focused on problem-solving.

Context-Optimized Memory Bank — Reduce AI token usage with structured documentation and cache-aware reading strategies

Claude Code skill for optimizing oversized CLAUDE.md files using progressive disclosure

This repository introduces the Letta framework, empowering developers to build LLM-based agents with long-term, persistent memory and advanced reasoning capabilities. It leverages concepts from MemGPT to optimize context usage and enable multi-agent collaboration for real-world applications like research, HR, and task management.

⚡ 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.

Helm Charts for installing reShapr components on Kubernetes

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

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.

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

MCP proxy server — 85-96% token savings via lazy tool loading & fuzzy search across 100+ MCP servers. npm i mcp-tool-search

MCP servers as CLI tools — built for AI agents

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

Context optimization for AI coding assistants — 99% token savings, zero configuration, no LLM dependency

Central repository for the reShapr project community health assets.