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.
Reduce costs on LLM API usage by compressing requests without changing the responses.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeLocal 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.
llmtrim has 222 stars on GitHub. It has been forked 22 times. llmtrim is written mainly in Rust. It has been in active development since 2026. llmtrim is available under the MPL-2.0 license. Its main topics are agentic-coding, ai, anthropic, claude-code.
What is 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.
Is llmtrim open source?
llmtrim is an open-source project. It is released under the MPL-2.0 license.
Is llmtrim free?
Yes. llmtrim is free and open source — you can use, modify and self-host it. Its MPL-2.0 license is copyleft: if you distribute a modified version, it must remain under the same license.
What license does llmtrim use?
llmtrim is available under the MPL-2.0 license.
What language is llmtrim written in?
llmtrim is written mainly in Rust.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/fkiene-llmtrim.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.