Surgical token-reduction companion for Claude Code and other AI coding agents

Tokenade — cut your AI coding agent's token bill. Installs the Tokenade CLI (a local, paid token-reduction tool; activate via your browser).

Framework-aware code intelligence MCP server — 60 framework integrations, 81 languages, up to 99% token reduction

MCP server for MinerU document parsing API - optimized for Claude Code with 73% token reduction

OpenCode plugin implementing Rust Token Killer (RTK) token reduction techniques

Token reduction & persistent memory for Pi coding agent — compress tool outputs, save decisions across sessions, survive compaction, backed by Obsidian

Extensible Reduced Object Notation — lossless data serialization achieving ~80% token reduction for LLM contexts

Convert OpenAPI/Swagger specs to AI-friendly formats with 85%+ token reduction

RTK token reduction extension for pi-coding-agent - reduces LLM token consumption 60-90% by intelligently filtering tool output

We measured every token-reduction claim against real usage. One technique survived: ANSI stripping. The proofs are in bench/.

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with Skeletonization (92% token reduction).

MCP multiplexer with progressive discovery, parallel batch calls, code execution, and up to 90% token reduction

Universal LLM Context Optimization - 90% Token Reduction

RTK token reduction extension for pi-coding-agent - reduces LLM token consumption 60-90% by wrapping commands with external rtk binary and intelligently filtering tool output

OpenClaw skill for ML-powered DOM snapshots - 95% token reduction for browser automation

MCP middleware that prunes Playwright accessibility snapshots for LLM agents. Zero ML, 75-95% token reduction, all refs preserved.

Token-optimized MCP Server for n8n workflows - 80%+ token reduction

Convert JSON to DCP positional-array format for AI agents — 40-70% token reduction

Token reduction plugin for coding agents - reduces LLM token consumption by 60-90%

Static project review + Token-reduction agent for Claude Code workflows: measures, diagnoses, plans, executes, verifies