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.; gemini-mcp-tool: This tool acts as a Model Context Protocol (MCP) server, enabling AI assistants, particularly Claude, to interact with the Gemini CLI. It allows AI to leverage Gemini's large token window for comprehensive analysis of extensive files and codebases.
Reduce LLM token usage and API costs for AI agents.
Leveraging Gemini for deep analysis of large files and codebases through AI assistants