Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens...
Copy the install, test the workflow, then decide if it earns a permanent slot.
The signal is softer here. Treat it like a pattern source unless it solves a very specific gap.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
GitHub health unknown. no security policy. 0 open issues make this testable, but not something to trust blind.
AI Agent
Claude Code
Model
Claude
Fastest way to find out if llmtrim belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/fkiene/llmtrim ~/.claude/agents/llmtrimRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/llmtrimNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ agents/ │ └─ llmtrim/ ← installs here └─ settings.json
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also embeddable as a library (Rust, Python, Ruby, Kotlin, Swift).