llmtrim
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 an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
fkiene/llmtrim
View on GitHub ↗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 an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
llmtrim grew +7.5% in the last 30 days, ranks 105th of 268 in LLM Gateway & Routing, actively maintained, last commit 4 days ago.
Star trajectory
115 days tracked+7.5% in 30d, above the LLM Gateway & Routing median of +2.1%.
Last commit 4 days ago, fresher than the median of 5d.
How it compares in LLM Gateway & Routing
Ranked 105th of 268 by stars.
- Language
- Rust
- License
- Mozilla Public License 2.0
- Contributors
- 5
- Forks
- 23
- Watchers
- 4
- Open issues
- 3
- Releases
- 64
- Created
- 2026-06-07
- Stars this week
- +8
You've seen where llmtrim stands today.
Get the moves before everyone else: the 5 LLM Gateway & Routing repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.