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).
Not yet testedsource: GitHubhomepageRustMPL-2.0commit 9586780b3ed9
Rust, MPL-2.0 licensed. The project labels itself: agentic coding, ai, anthropic, claude code, cost reduction, developer tools, llm and llmops.
llmtrim has not been verified yet.
Measured by Argusic on a fresh machine every time. Every number links to its evidence.
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
No recorded runs.
Topics (from GitHub)
agentic-codingaianthropicclaude-codecost-reductiondeveloper-toolsllmllmopsmcpmitm-proxyopenaipromptprompt-compressionprompt-engineeringproxyrusttoken-optimization
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/llmtrim)Questions
- Does llmtrim run?
- llmtrim has not been fully verified yet. No recorded run has produced a verdict yet.
- How did Argusic test llmtrim?
- On a fresh, disposable machine, with every command recorded. 0 attempts are recorded, and the full method is on the methodology page.
- Where is the evidence for llmtrim?
- All 0 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.