lumen

All of these "hacks" are snakeoil and I think deep down we all know. Whether it's caveman, RTK, or whatever other vibe-coded productivity/token cost saving hacks/skills/claude.md. What I had success with (although benchmarks are older) is to index the codebase with a dedicated local code embedding model. It's a bit expensive on the CPU side but in my benchmarks it reduced token use and wall clock time significantly. Of course, it's always dependent on statistical noise + host system load, and running sufficiently large benchmarks is simply too expensive, so take em with a grain of salt. Why does it work you may ask? Well, LLMs basically brute force words/phrases and pipe that into find/grep/pgrep/whatever (or as recently discussed here write a python script for it - https://news.ycombinator.com/item?id=49654229). Semantic search looks for

Besides some of the obvious hacks to reduce token usage, properly indexed code bases (think IntelliJ) reduce token usage significantly (30%-50%, while keeping or exceeding result quality compared with baseline) as shown with https://github.com/ory/lumen Anthropic is not incentivized to reduce token use, only to increase it, which is what we are seeing with Opus 4.6 and now they are putting the screws on

Does this solve indexing of codebases like Cursor does, or do you still need tools / plugins like Lumen (https://github.com/ory/lumen) for that in order to work in larger codebases without wasting tens of thousands of tokens on tool calls and brute force guessing with grep?

Why does is this ridiculous thing trending on HN? There are actually good tools to reduce token use like https://github.com/thedotmack/claude-mem and https://github.com/ory/lumen that actually work!