Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens

Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o... by jemmyw on Friday June 05, 2026 @09:43AM (#48412469)

I've tried rtx and lean-ctx and these tools seem to end up confusing the agent more than helping. Any saving is irrelevant if the agent decides to work around the tool and makes even more calls than it would otherwise.

I don't know about cost saving, but if it's keeping the context size down I've had a lot better results using subagents to keep a higher order conversation clean for longer.

[ Parent | on HN ]

Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o... by lxn on Friday June 05, 2026 @10:42AM (#48413227)

I looked into lean-ctx and decided not to use it. It has a very specific use case, and it's good when your interaction with the repository is read-only. When you want to edit, then the model has to read the whole file anyway. It's a cool tool, but it has a very narrow use case where it delivers the performance it claims.

[ Parent | on HN ]

Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o... by exitb on Friday June 05, 2026 @09:55AM (#48412632)

Subagents help with costs too, as they can run on much cheaper models.

[ Parent | on HN ]

Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o... by mywittyname on Friday June 05, 2026 @12:49PM (#48415122)

Also, most of the time when I'm having an agent look through logs or output, it's grepping for the bits of data relevant to its actions.

[ Parent | on HN ]