97% token reduction for AI coding sessions — zero deps, 31 languages, MCP server

serena MCP (38% less tokens). Quick setup: npx serena-slim --setup

SigMap AI context engine — VS Code extension. 96.9% token reduction, 80.0% retrieval hit@5, 29 languages. Works with Copilot, Claude, Cursor, Windsurf, Gemini.

sequential-thinking MCP (0% less tokens). Quick setup: npx sequential-thinking-slim --setup

context7 MCP (0% less tokens). Quick setup: npx context7-slim --setup

MCP algorithm for reducing LLM coding agent token usage via vectorized prompts and interpreted code stack.

chrome-devtools MCP (69% less tokens). Quick setup: npx chrome-devtools-slim --setup

Same AI answers, ~65% fewer tokens. Manifest V3 extension that injects a compression preamble on 19 AI chat sites. Pure client-side, no accounts, no API keys.

everything MCP (58% less tokens). Quick setup: npx everything-slim --setup

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

sqlite MCP (33% less tokens). Quick setup: npx sqlite-slim --setup

Surgical middleware for LLMs. Reduces token waste by 40-60% using Triple-Tier Memory (Anchor + Fact Sheet + Buffer) and Semantic Caching. Built for production-grade branding & cost-recovery.

playwright MCP (73% less tokens). Quick setup: npx playwright-slim --setup

notion MCP (52% less tokens). Quick setup: npx notion-slim --setup

memory MCP (44% less tokens). Quick setup: npx memory-slim --setup

filesystem MCP (54% less tokens). Quick setup: npx filesystem-slim --setup

git MCP (58% less tokens). Quick setup: npx git-slim --setup

github MCP (56% less tokens). Quick setup: npx github-slim --setup