Sign in Sign up
cargo

llmtrim-core

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).

cargo View on Cargo github View on Github

Activity

Latest release
6d ago
Total releases
55
Cadence
~daily
Last 12 months
55

Reach

Downloads
1.8k
Stars
229

Details

License
MPL-2.0
First release
Jun 13, 2026
Releases
Version Released
0.13.4 patch
0.13.3 patch
0.13.2 patch
0.13.1 patch
0.13.0 minor
0.12.6 patch
0.12.5 patch
0.12.4 patch
0.12.3 patch
0.12.2 patch
0.12.1 patch
0.12.0 minor
0.11.12 patch
0.11.11 patch
0.11.10 patch
0.11.9 patch
0.11.8 patch
0.11.7 patch
0.11.6 patch
0.11.5 patch
0.11.4 patch
0.11.3 patch
0.11.2 patch
0.11.1 patch
0.11.0 minor
0.10.2 patch
0.10.1 patch
0.10.0 minor
0.9.4 patch
0.9.3 patch
0.9.2 patch
0.9.1 patch
0.9.0 minor
0.8.1 patch
0.8.0 minor
0.7.0 minor
0.6.3 patch
0.6.2 patch
0.6.1 patch
0.6.0 minor
0.5.0 minor
0.4.0 minor
0.3.2 patch
0.3.1 patch
0.3.0 minor
0.2.1 patch
0.2.0 minor
0.1.13 patch
0.1.12 patch
0.1.11 patch
1–50 of 55