claude-context

I remember thinking the same thing and this articles goes over most of the arguments here - https://milvus.io/blog/why-im-against-claude-codes-grep-only... When it came out and I think it was Boris from Anthropic that said they experimented a lot with Vector Search and grep just worked better. You can try it out using the Claude-Context MCP - https://github.com/zilliztech/claude-context

Claude Code doesn't do anything with semantic search or embeddings out of the box. They use a simple grep tool instead. Neither does OpenAI's Codex CLI - you can confirm that by looking at the source code https://github.com/openai/codex Cursor and Windsurf both use semantic search via embeddings. You can get semantic search in Claude Code using this unofficial plugin: https://github.com/zilliztech/claude-context - it's built by and uses a managed vector database called Zilliz Cloud.

Every AI coding tool has a search problem. Claude uses grep. Cursor does basic vector search. Context retrieval? Honestly, pretty mediocre. As a co-founder of a vector database company, I’ve realized: the only way to understand real developer pain is to use these tools every day — not just sit in strategy meetings. Tried Claude Code. Loved the idea: delegating tasks from the terminal feels magical. But hit a wall fast — grep-based search doesn’t understand semantics. It finds strings, not meaning. Cursor? A good start with vector search, but still shallow. No deep understanding of code structure or intent. That pain point became our opportunity. The more I used Claude, Cursor, Windsurf… the clearer it became: AI tools lack true semantic code understanding. So we built Code Indexer CLI: One-click indexing of your codebase Fast, semantic re