Why Claude Code Replaced Vector Search with Grep

Coding agents often feel like they secretly maintain persistent semantic indexes of your repository. In reality, Claude Code dropped its early vector database prototype entirely in favor of ripgrep, glob, and iterative tool calls. This deep dive unpacks how Claude Code and Codex manage project context, why staleness and privacy make precomputed embeddings fragile, and where server-side prompt caching actually helps with token costs without remembering your codebase. Key sources: • Anthropic, How Claude remembers your project — https://code.claude.com/docs/en/memory • Anthropic, Explore the context window — https://code.claude.com/docs/en/context-window • Anthropic, How Claude Code works — https://code.claude.com/docs/en/how-claude-code-works Episode 6286 — myweirdprompts.com/n/6286 (permanent short link: myweirdprompts.com/359752)