# fkiene/llmtrim

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/fkiene-llmtrim).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

64 stars · 4 forks · Rust · AGPL-3.0

## Links

- GitHub: https://github.com/fkiene/llmtrim
- Homepage: https://www.npmjs.com/package/@llmtrim/cli
- awesome-repositories: https://awesome-repositories.com/repository/fkiene-llmtrim.md

## Description

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).

## Tags

### Part of an Awesome List

- [AI Assistant Tools](https://awesome-repositories.com/f/awesome-lists/productivity/ai-assistant-tools.md) — Local proxy for compressing LLM API requests.
- [AI Assistants and Tools](https://awesome-repositories.com/f/awesome-lists/productivity/ai-assistants-and-tools.md) — Local proxy for compressing LLM API requests.