headroom: Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. It achieves the same answers with a fraction of the tokens.; token-optimizer-mcp: Token Optimizer MCP is a Model Context Protocol (MCP) server designed to reduce context window usage for AI tools like Claude Code and Claude Desktop by 60-90%. It achieves this through intelligent caching, Brotli compression, and smart tool replacements, storing compressed content externally in SQLite.
Reduce LLM token usage and API costs for AI agents.
Reduce token costs and improve performance for AI code assistants by optimizing context window usage.