L
llmtrim
fkiene/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).
★198stars
Rust
MPL-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Plugins, MCP & Skills project leveraging agentic-coding and anthropic, built with Rust, open-source
Who made it?Maintained by fkiene team, 198⭐ on GitHub, #1283 out of 2373 in Plugins, MCP & Skills
Why does it exist?The fkiene team recognized that existing agentic-coding tools in Plugins, MCP & Skills were hard to use. llmtrim was designed to make anthropic more accessible.
What can it do?Key use cases: claude-code, cost-reduction, developer-tools
How to install with AI?Use an AI coding assistant to run cargo build and handle the compilation setup from the README.
🔗 github.com/fkiene/llmtrim | 官网 https://www.npmjs.com/package/@llmtrim/cli
🔗 github.com/fkiene/llmtrim | 官网 https://www.npmjs.com/package/@llmtrim/cli
Topics
agentic-codingaianthropicclaude-codecost-reductiondeveloper-toolsllmllmopsmcpmitm-proxyopenaipromptprompt-compressionprompt-engineeringproxyrusttoken-optimization