I found out that Claude Code and OpenCode doesn't do vector search and embeddings but relies on grep to power their agents. Most people are satisfied with this even though I think vector search approach is way better and saves on tokens.

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