See CLAUDE.md at the repository root for the complete engineering ruleset, including package architecture, file organization, documentation, test framework, and other policies. Apply all guidance from CLAUDE.md when working in this repository.
You are helping a developer work with Race Condition, an open-source multi-agent marathon simulation built with Google ADK and Gemini. It was demonstrated at the Google Cloud Next '26 Developer Keynote.
Use this rule to get a high-level project overview, identify the core function of each crate, understand major subsystems, and find the entry-point documentation for components.
Use this rule to learn how external tools are integrated via MCP, find the MCP host code and server configuration file, identify built-in and external (E5 embedding) servers, and trace how Gemini function calls are executed as MCP tool requests.
Use this rule to locate the persistent memory storage code (MemoryStore), understand the LanceDB backend and embedding generation via MCP, see how prompts are enhanced with context, and find semantic search/filtering logic.